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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to confrontational and aggressive language

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

    slang, profanity, gangster terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finanzas
    -0.34
     cyclisme
    -0.33
    áctenos
    -0.30
     novel
    -0.29
     cuantos
    -0.28
     exportación
    -0.28
     engran
    -0.28
    principalTable
    -0.28
    ModelSerializer
    -0.27
     mété
    -0.27
    POSITIVE LOGITS
     autorytatywna
    0.75
     ghetto
    0.68
    \{\\
    0.65
     Ghetto
    0.65
    IsMutable
    0.61
    ajuku
    0.60
     defaultstate
    0.58
    cshtml
    0.58
     ویکی‌پدی
    0.57
    sizeCache
    0.57
    Act Density 0.082%

    No Known Activations