Language models can explain neurons in language models

Company news OpenAI Source language: English

We use GPT-4 to automatically write explanations for the behavior of neurons in large language models and to score those explanations.

Excerpt

We use GPT-4 to automatically write explanations for the behavior of neurons in large language models and to score those explanations.

Short excerpt from the source — open the original for the full text.

Sources

← Back to the daily brief