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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of "Dark" or "dark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlSchema
    -0.71
     ComVisible
    -0.67
    PreExecute
    -0.60
    toThrow
    -0.58
    بوابة
    -0.56
    ScopeManager
    -0.55
    ayage
    -0.55
    ricians
    -0.54
    Estimation
    -0.52
    Kaynakça
    -0.50
    POSITIVE LOGITS
     Dark
    0.83
    Dark
    0.81
     tree
    0.73
    tree
    0.73
    ك
    0.69
    flat
    0.66
     DARK
    0.65
    Flat
    0.65
     Conſ
    0.64
     Diſ
    0.64
    Act Density 0.231%

    No Known Activations