Fixed slider loading bug

Updated and partitioned glossary

Moved glossary button to header instead of hidden in sidebar

Added simpler ablation experiment buttons to add full categories

Added pre-built prompts for app and chatbot

Bug fix: type issue with models leading to gibberish outputs

Replace token references with word in output selection stage

Rename L#-H# notation to L#-D# for detector consistency

Reduce jargon across UI for younger/less-technical audiences

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

Fixed duplicate activation store bug

added color swatches for easy mapping from attention categories to BertViz

display attention category scores in order

completed the rest of the explanation improvements from JARVIS audit

New models chosen and rag docs updated

Attention refactor, better categorization and explanation

Fixed glossary UI to be cleaner

Added glossary embeddings and explanations

ablation experiment fixes, better UI and full sequence comparison

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

Add drag-to-resize on chat window left edge

Added message greeting to chatbot

Reset chat history on browser refresh to show greeting

Add greeting message to chatbot on first open

Resolve merge conflicts in README.md and todo.md

feat: Add AI chatbot with Gemini integration and RAG support

cleanup for merge

chore: remove unused code, imports, and deprecated functions

conductor setup

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

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

rules change for simple git commit messages

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

Add educational explanations to pipeline stages (Agent C): embedding lookup table, MLP knowledge storage, attention viz guide

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

Add comprehensive test suite for utility modules (73 tests)

Refactor: Replace heatmap with pipeline explanation visualization

heatmap implementation

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

Fixed errors for beam search refactor

Switched to beam search instead of single token

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

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 token predictions not being collected - changed condition to check for block_outputs and norm_parameters instead of logit_lens_parameter

Implement PHASE 3: Tokenization Explanation Section - Created components/tokenization_panel.py with three-column layout - Added HTML/CSS-based static tokenization diagram - Integrated tokenization panel into main_panel.py - Added update_tokenization_display() callback - Added CSS styling with hover effects and connecting lines - Implemented comparison mode support with vertical stacking

PHASE 2: UI Component Removal & Cleanup - Removed Check Token feature, Bottom Experiments section, certainty display, and top_attended section from layer accordions. Cleaned up related CSS.