Transformer models that predict answers to addition questions
Philip Quirke
AI & ML interests
AI Safety, Mechanistic Interpretability, Conservation
Recent Activity
published a dataset about 1 hour ago
PhilipQuirke/detect-hallucinations-samples published a dataset about 1 hour ago
PhilipQuirke/detect-hallucinations-results updated a dataset 5 days ago
PhilipQuirke/detect-hallucinations-results