artifact
active
artifact:safety-research-assistant-axis-github-repository

safety-research/assistant-axis GitHub repository

Code and full transcripts of case studies released alongside the paper

Neighborhood — ranked by edge-count

Papers (1)

paper

Frameworks (1)

framework
  • Assistant Axis
    about
    Contrast vector between mean default Assistant activation and mean of all fully role-playing role vectors; main contribution of the paper