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. 87
    Prev
    Next
    INDEX
    Explanations

    references to video content or links related to viewing and identifiers

    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
    clair
    -0.71
    ippi
    -0.69
    yne
    -0.64
    ync
    -0.63
    oga
    -0.62
    sterdam
    -0.61
    retty
    -0.61
    affe
    -0.61
    ️
    -0.59
    ayne
    -0.59
    POSITIVE LOGITS
     EntityItem
    0.74
    agogue
    0.74
    イト
    0.74
    tics
    0.72
    ْ
    0.72
    soType
    0.68
    phrine
    0.65
    tical
    0.65
    グ
    0.63
    tic
    0.62
    Activations Density 0.057%

    No Known Activations