Skip to content

RelativelyFine/refusal_direction

View on GitHub ↗Related repositories →

Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

active 2024-11-13 → 2025-01-01 (UTC)

Complete coverage27,401 / 27,401 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-09-29 (UTC)
Events
18
Pushes
11
Pull requests
2
Issues
0
Stars
0
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 50 days from 2024-11-13 to 2025-01-01. Pushes: 11 total, peak 3 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 0 total, peak 0 in a day. Comments: 1 total, peak 1 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
RelativelyFine11911
BusinessJoe3210

Recent activity

Latest issues, pull requests and releases

  • Pull request#1RelativelyFine2024-12-04 21:58
  • Issue comment#1RelativelyFine2024-12-04 21:58
  • Pull request#1BusinessJoe2024-12-04 21:51

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.