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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions, limitations, or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     архивлан
    -0.58
     مفص
    -0.52
    خصة
    -0.52
     gebeurt
    -0.52
    ГЛА
    -0.51
    IEU
    -0.47
     AssemblyProduct
    -0.47
    جغرافيا
    -0.46
    middels
    -0.45
    komt
    -0.45
    POSITIVE LOGITS
     Axiom
    0.63
     חיצוניים
    0.60
     للاسماء
    0.58
     ***!
    0.58
    RectangleBorder
    0.58
     Woodlands
    0.57
     Cze
    0.57
    BeginContext
    0.56
    aarrggbb
    0.55
     wireType
    0.55
    Act Density 1.137%

    No Known Activations