https://arxiv.org/abs/2510.01070
Bartosz Cywiński
bcywinski
AI & ML interests
Mechanistic Interpretability
Recent Activity
updated
a model
42 minutes ago
bcywinski/qwen3-4b-taboo-gold
published
a model
43 minutes ago
bcywinski/qwen3-4b-taboo-gold
authored
a paper
4 days ago
Eliciting Secret Knowledge from Language Models
Organizations
None yet