3 sources · 2 topics

Library

Built automatically from the sources listed in each post.

Persuasion & CMV data

paperWinning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions ↗
cited in Is there a "persuasion" direction inside the model?

Steering & representation engineering

paperRepresentation Engineering: A Top-Down Approach to AI Transparency ↗
Placeholder note: my one-line takeaway.
cited in Is there a "persuasion" direction inside the model?
paperSteering Language Models With Activation Engineering ↗
cited in Is there a "persuasion" direction inside the model?