Gonçalo Paulo

MrGonao

AI & ML interests

Interpretability

Recent Activity

updated a collection 2 days ago
Replicating emergent misalignment
updated a model 2 days ago
MrGonao/edu_incorrect_subtle_reformatted_2
published a model 2 days ago
MrGonao/edu_incorrect_subtle_reformatted_2
View all activity

Organizations

EleutherAI's profile picture Sapienza University of Rome's profile picture delphi's profile picture