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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 232
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those of athletes and coaches

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

    No Comments

    Negative Logits
    yssey
    -0.57
    aceae
    -0.54
     Bros
    -0.48
    redits
    -0.48
     indirectly
    -0.48
    omics
    -0.47
    BuyableInstoreAndOnline
    -0.47
    ivities
    -0.46
     Trin
    -0.46
     Jacobs
    -0.46
    POSITIVE LOGITS
     anonymous
    0.50
    king
    0.48
    standard
    0.47
    cible
    0.47
    cases
    0.47
    vol
    0.47
    plain
    0.47
    lethal
    0.47
     contiguous
    0.46
    pn
    0.45
    Activations Density 0.343%

    No Known Activations