AlphaUncommon
andyrdt/refusal_direction
Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
- Owner
- andyrdt (personal account)
- Stars
- Stars: 480
- Forks
- Forks: 126
- Language
- Python
- License
- Apache-2.0
- Created
- 2024
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in Python
All Python repos- meituan-longcat/LongCat-NextStars: 480PythonAlpha
- hexsecteam/DroidHunterStars: 480PythonAlpha
- nv-tlabs/dvltStars: 480PythonAlpha
- clustershell/clustershellStars: 480PythonAlpha
- brandon-rhodes/python-sgp4Stars: 480PythonAlpha
- nephila/djangocms-blogStars: 480PythonAlpha