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

    Neuronpedia

    INDEX
    Explanations

    phrases related to humor and laughter

    oai_token-act-pair · gpt-3.5-turbo

    instances of laughter and related expressions of amusement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entrusted
    -0.75
     inhabited
    -0.72
    jas
    -0.68
    ction
    -0.68
    ded
    -0.66
     cogn
    -0.66
    ĪĴ
    -0.65
    appropri
    -0.65
    occupied
    -0.65
     populated
    -0.65
    POSITIVE LOGITS
    Laughs
    1.09
    laughs
    1.08
    laughter
    1.04
    laugh
    0.87
    ause
    0.86
    aughs
    0.82
    swers
    0.78
    HAEL
    0.76
    pause
    0.74
    terness
    0.73
    Act Density 0.021%

    No Known Activations