A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID
A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patch
Deep Dive
Computer Science > Computation and Language arXiv:2609.30287 (cs) [Submitted on 8 Sep 2026] Title: A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID Authors: Paweł Blicharz , Miłosz Grunwald View a PDF of the paper titled A Mechanistic St