Knowledge Tree
Relations (1)
related 0.10 — supporting 1 fact
The relationship is established because analysts can determine if a specific [neuron] is causally responsible for a [hallucination] by observing model behavior during activation experiments as described in [1].
Facts (1)
Sources
LLM Observability: How to Monitor AI When It Thinks in Tokens | TTMS ttms.com 1 fact
procedureAnalysts can investigate if a specific neuron is causally responsible for a hallucination by running the model with and without that neuron active.