Attention refactor, better categorization and explanation

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

chore: remove unused code, imports, and deprecated functions

fix(utils): Export generate_bertviz_model_view_html from package

Fix multi-layer ablation to ablate all heads simultaneously

Switch attention viz to head_view and add categorization (Agent D)

Refactor: Replace heatmap with pipeline explanation visualization

heatmap implementation

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

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

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

completed ablation experiment implementation

Fix accordion data flow and remove all legacy Cytoscape code

Replace Cytoscape with accordion-based layer view

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

Fix: Export categorize_single_layer_heads from utils package

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

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

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

Added model config for automatic model parameter detection

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