Fixed chatbot bubble generation bug

Fixed single-token sequence UI bug

Fixed ablation original prompt generation bug

Fixed ablation graphs first token population, still need to fix original graphs when no beam selected

Fixed ablation graphs first token population, still need to fix original graphs when no beam selected

Fixed model-switching bug with activation store clearing

Added loading screen to pipeline steps for better UX

completed the rest of the explanation improvements from JARVIS audit

Attention refactor, better categorization and explanation

Fixed glossary UI to be cleaner

Chatbot improvements: UI cleaning, chat streaming, typing animation, and better markdown formatting

ablation experiment fixes, better UI and full sequence comparison

feat(output): Add token scrubber with per-position top-5 next-token probabilities

Added full sequence to analysis, still need to do output scrubber

Add Dockerfile for Hugging Face Spaces deployment

Added message greeting to chatbot

cleanup stuff

Migrate from Gemini to OpenRouter API

Add Hugging Face deployment prep: .gitignore, load_dotenv, API tests

Resolve merge conflicts in README.md and todo.md

feat: Add AI chatbot with Gemini integration and RAG support

chore: remove unused code, imports, and deprecated functions

conductor setup

conductor(checkpoint): Checkpoint end of Phase 3: Visualization & Feedback Loop

conductor(checkpoint): Checkpoint end of Phase 2: Frontend Control Panel

Fix multi-layer ablation to ablate all heads simultaneously

Fix ablation head selection: handle old data format, prevent spurious selections on render

Fix 5 UI issues: comparison button, tokenization layout, expandable attention categories, BertViz instructions, multi-layer ablation

Refactor analysis scope and enhance attention UI (Agents F and G)

Improve UI clarity: rename generation settings labels and remove score display

Refactor: Replace heatmap with pipeline explanation visualization

Fix heatmap colorbar config

heatmap implementation

Ablation updated for full sequence, needs refactor for front-end and workflow

Fixed errors for beam search refactor

Fix storage quota error by using memory storage and add type safety checks

Better explanations, moved transformer layer diagram to be more visible

Fix: Add actual_output to session store to display final token and highlight significant layers

Update layer highlighting to 100% threshold for actual output token only

Improve explanations: optimize head categorization and comparison thresholds, enhance ablation explanation, rewrite all tooltips for high school level

Clean up: fix significant layer threshold to 50%, remove unused logit lens parameter, remove certainty calculations

Add ablation experiment before/after comparison with Reset button

Fix ablation: add attention_modules to session store so ablation can find attention layers

Add comprehensive debugging to ablation data flow

Fix ablation data missing input_ids: preserve from original activation data

Fix Run Ablation button: correctly map button indices to layer numbers when layers are displayed in reverse order

Refine layer organization: add title to diagram, move graph below layers, give Residual a box, reorder Explore button

Reorganize Layer-by-Layer Predictions: move diagram to main container, reorder sections, update arrows, increase threshold to 75%

Fix norm_selection type mismatch and ensure norm_parameters are always selected - Changed auto-selection to return list instead of string - Updated run_analysis to handle norm_patterns as list - Added norm_parameters requirement to Run Analysis button

Fix callback error: use model-status instead of non-existent status-message