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. 788
    Prev
    Next
    INDEX
    Explanations

    the token "pr", the word "two" or other two-letter tokens in the middle of words

    numeric values and their adjacent words.

    oai_token-act-pair · gpt-4-turbo

    Letters “or” in the middle of words

    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    No Known Activations