Arthur Conmy
Scholar

Arthur Conmy

Google Scholar ID: n4HIyXQAAAAJ
Google DeepMind
AGI SafetyAI SafetyInterpretabilityMechanistic InterpretabilityMachine Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
2,569
 
H-index
18
 
i10-index
20
 
Publications
20
 
Co-authors
20
list available
Contact
No contact links provided.
Publications
16 items
How do LLMs Compute Verbal Confidence
2026
Cited
0
Automatically Finding Reward Model Biases
2026
Cited
0
Simple LLM Baselines are Competitive for Model Diffing
2026
Cited
0
Fluid Representations in Reasoning Models
2026
Cited
0
Building Production-Ready Probes For Gemini
2026
Cited
1
Base Models Know How to Reason, Thinking Models Learn When
2025
Cited
0
Eliciting Secret Knowledge from Language Models
2025
Cited
0
Thought Anchors: Which LLM Reasoning Steps Matter?
2025
Cited
0
Resume (English only)
Co-authors
20 total
Neel Nanda
Neel Nanda
Mechanistic Interpretability Team Lead, Google DeepMind
Senthooran Rajamanoharan
Senthooran Rajamanoharan
Google DeepMind
Co-author 3
Co-author 3
Aengus Lynch
Aengus Lynch
University College London
Co-author 5
Co-author 5
Rohin Shah
Rohin Shah
Research Scientist, Google DeepMind
Jacob Steinhardt
Jacob Steinhardt
Stanford University
Rowan Wang
Rowan Wang
Unknown affiliation