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

    Neuronpedia

    INDEX
    Explanations

    references to humor, satire, and comedic elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cardiaque
    -0.30
     ligiloj
    -0.30
    Географиясе
    -0.29
    ampilan
    -0.29
     pulsera
    -0.28
    IVEREF
    -0.28
     convaincre
    -0.28
     pulseira
    -0.27
    getSettings
    -0.27
     exud
    -0.27
    POSITIVE LOGITS
     humor
    1.30
     humorous
    1.23
     humour
    1.20
     Humor
    1.17
     comedic
    1.12
     hilarious
    1.09
     joke
    1.09
     joking
    1.08
    Humor
    1.08
     jokes
    1.07
    Act Density 0.575%

    No Known Activations