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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 314
    Prev
    Next
    INDEX
    Explanations

    references to expectations or behaviors typically associated with certain roles or professions

    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
    upon
    -0.60
     Maurice
    -0.58
    forge
    -0.56
     Yah
    -0.56
    DOWN
    -0.56
     Seller
    -0.55
     Mubarak
    -0.55
     Mazda
    -0.53
     Orig
    -0.53
    atorium
    -0.52
    POSITIVE LOGITS
    irlf
    0.77
    imity
    0.72
    tones
    0.69
    olesc
    0.69
    WithNo
    0.68
    enhagen
    0.67
    amina
    0.63
     endings
    0.63
    ftime
    0.63
    leneck
    0.61
    Activations Density 0.296%

    No Known Activations