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

    Neuronpedia

    INDEX
    Explanations

    expressions and concepts related to humor and sarcasm

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

    humorous and witty language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BASEPATH
    -0.56
     Houſe
    -0.55
    ineſs
    -0.54
     Jefus
    -0.53
     increí
    -0.53
     Infórmanos
    -0.52
    rament
    -0.51
     للاسماء
    -0.50
     houſe
    -0.49
     Chrift
    -0.49
    POSITIVE LOGITS
     humorous
    1.00
     witty
    1.00
     sarcastic
    0.93
     comical
    0.80
     ironic
    0.69
     sarcas
    0.69
     satirical
    0.68
     whimsical
    0.67
     amusing
    0.63
     comedic
    0.63
    Act Density 0.008%

    No Known Activations