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

    Neuronpedia

    INDEX
    Explanations

    references to humor and comedy in various contexts

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

    humor and humour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.58
    ClientRect
    -0.56
    ❚
    -0.56
     CreateTagHelper
    -0.55
     aufs
    -0.55
     nakalista
    -0.55
    RTGC
    -0.54
    gestone
    -0.54
     Infórmanos
    -0.52
    argate
    -0.51
    POSITIVE LOGITS
     humor
    1.93
     humour
    1.77
     Humor
    1.72
    Humor
    1.70
    humor
    1.67
    humour
    1.52
     humorous
    1.33
    幽默
    0.95
     comedy
    0.90
     comedic
    0.78
    Act Density 0.004%

    No Known Activations