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

    Neuronpedia

    INDEX
    Explanations

    phrases related to humor or jokes, particularly when someone is amused

    oai_token-act-pair · gpt-3.5-turbo

    instances of humor and comedic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antioxid
    -0.88
    GoldMagikarp
    -0.86
    Balt
    -0.83
     behavi
    -0.79
    PDATE
    -0.76
    DAQ
    -0.75
    HUD
    -0.72
    natureconservancy
    -0.71
    CLASSIFIED
    -0.71
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
    POSITIVE LOGITS
    ividual
    0.92
    ogun
    0.73
    itially
    0.70
    othal
    0.70
    ruary
    0.68
    onga
    0.66
    ecause
    0.65
    irlf
    0.63
    bidden
    0.61
    initely
    0.61
    Act Density 17.895%

    No Known Activations