AgentDish directory
moe
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
#1057
↓ -1
Senbonzakura
Open-source tool for removing refusal behavior from open-weight transformer language models by identifying and orthogonalizing refusal directions in activation space. |
Developer Tools / AI Model Editing / Alignment Research | 74 | ↓ -1 | 1 hour ago | Details |