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

    Neuronpedia

    INDEX
    Explanations

    instances of laughter and humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cookieParser
    -0.38
     desea
    -0.29
     wishes
    -0.28
    noche
    -0.28
    setdefault
    -0.27
     wünschen
    -0.25
    readyState
    -0.25
    databinding
    -0.24
    -0.24
     loans
    -0.24
    POSITIVE LOGITS
     laugh
    1.25
     laughing
    1.23
     laughter
    1.16
     laughed
    1.15
    laugh
    1.14
     tertawa
    1.09
     Laugh
    1.09
    Laugh
    1.09
    laughing
    1.07
    Laughing
    1.07
    Act Density 0.177%

    No Known Activations