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

    Neuronpedia

    INDEX
    Explanations

    configuration settings and parameters related to system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code-like identifiers and configuration parameters, especially those with underscores, double-underscore suffixes, symbols (e.g., $) or version digits, often appearing in assignments and field/method declarations

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab

    programming identifiers

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.77
     Winaray
    -0.70
    UrlResolution
    -0.69
     noDo
    -0.68
    Tikang
    -0.67
     فريبيس
    -0.67
    KommentareTeilen
    -0.67
     nahilalakip
    -0.66
    :✨
    -0.66
     BoxDecoration
    -0.66
    POSITIVE LOGITS
    esModule
    0.39
    ToListAsync
    0.38
    所示
    0.36
    atás
    0.36
     onPostExecute
    0.35
     faptul
    0.34
    FieldNumber
    0.34
    newVal
    0.33
    باح
    0.33
    cfm
    0.33
    Act Density 1.006%

    No Known Activations