feat: implement PHASE 6 (BertViz button relocation) and PHASE 7 (CSS styling)

Phase 1: Backend infrastructure for token merging, layer-wise tracking, and head ablation

merge for ablation experiments

pycache shit

completed ablation experiment implementation

Fix experiments section visibility and improve ablation logic - Fix experiments section callback to show properly after analysis - Change mean ablation to use mean across ALL layers and tokens (not just selected layer) - Update UI description to clarify meaningless mean activation - Remove prevent_initial_call to ensure proper initialization

Add Experiments panel with mean ablation feature - Remove Divergent Layers summary from comparison panel (keep badges) - Add collapsible Experiments section after analysis - Implement Ablation Study with layer selection buttons - Add mean ablation function to replace layer activations with mean - Run ablation on both prompts and update results - Gray out ablated layer in accordion with visual indicator - Add CSS styling for experiments panel and ablated layers

Added prompt comparison visualizations

Fix callback error: remove non-existent second-visualization-section output

Fix meta tensor serialization error in safe_to_serializable

Add attention head categorization with colored badges to each layer accordion

Fix attention view display: always show section, remove Analysis Results, add debugging

Add simplified attention view with top-3 attended tokens and BertViz toggle button

feat: Add top-5 predictions with deltas, certainty meter, and bar charts in accordion panels

Improve layer spacing and header text

Fix accordion data flow and remove all legacy Cytoscape code

Replace Cytoscape with accordion-based layer view

cleanup and planning for next series of features

Refactor Check Token: Replace 4th edge with probability line graph

cleaned up file system

Implement edge hover tooltips with floating divs for better UX

Replace edge hover info with tooltip bubbles on visualization

Fix: Export categorize_single_layer_heads from utils package

Refactor: Move attention head categorization to on-demand per-layer display - Removed automatic Attention Head Categorization section from main panel - Created categorize_single_layer_heads() for per-layer categorization - Updated run_analysis to skip automatic head categorization - Enhanced node click callback to show layer-specific categorization - Analysis Results section now displays both BertViz and categorized heads on node click

Fix BertViz category visualization tensor stacking error and add head index labels

Feature update: Reorganize attention head categorization with BertViz visualizations for each category

Feature update: Check token now tries both with/without leading space and uses higher probability variant

Feature 6: Implement two-prompt difference analysis with divergent layer highlighting

Feature 5: Implement attention head detection and categorization with visual display

Feature 4: Replace BertViz head_view with model_view for hierarchical attention visualization

Feature updates: collapsible sidebar, toggle compare button, check token submit button, fix second graph visibility, improve check token debug output

Add check token feature with 4th edge and minimum opacity

Using final layer output instead of mlp for simpler computation

simplified vocab space projection

merged with pyvene

Added model config for automatic model parameter detection

Uses pyvene instead of just pytorch hooks, setting up for activation patching

Full visualization reorganization, handles model selection, parameter selection, visualizes graphs w/ bertviz onclick