https://github.com/carperai/polygraph

RLHF Mechanistic Interpretability and Deception
https://github.com/carperai/polygraph

Last synced: 10 months ago
JSON representation

RLHF Mechanistic Interpretability and Deception

• Host: GitHub
• URL: https://github.com/carperai/polygraph
• Owner: CarperAI
• License: mit
• Created: 2023-02-09T22:39:48.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2023-07-14T21:28:32.000Z (almost 3 years ago)
• Last Synced: 2025-01-08T02:15:24.225Z (over 1 year ago)
• Size: 6.28 MB
• Stars: 6
• Watchers: 4
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Polygraph

RLHF Mechanistic Interpretability and Deception