Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. 6
    4. 2054
    Prev
    Next
    INDEX
    Explanations

    "X who", "X which", "X that", etc., X is often "people", "someone", "many", "those"

    "someone who", "peoples who", "those whose", "bands that play"

    words associated with people or professions, and instances of the word 'who'.

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    No Known Activations