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

    Neuronpedia

    INDEX
    Explanations

    humor and comedic elements in the text

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

    jokes and humor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pushFollow
    -0.52
    printStackTrace
    -0.44
    Superview
    -0.43
     муніципалі
    -0.43
    calaureate
    -0.42
    fillType
    -0.42
     Champs
    -0.41
     Paglinawan
    -0.40
    abond
    -0.40
    agonia
    -0.40
    POSITIVE LOGITS
     chistes
    0.81
     jokes
    0.74
    jokes
    0.69
     joke
    0.66
    Jokes
    0.63
     Jokes
    0.61
     Económica
    0.59
     puns
    0.55
    joke
    0.54
     witty
    0.50
    Act Density 0.015%

    No Known Activations