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

    Neuronpedia

    INDEX
    Explanations

    laughter-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    instances of laughter or humorous expressions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ded
    -0.77
     bearer
    -0.71
    ction
    -0.70
     Components
    -0.66
     IX
    -0.66
    fell
    -0.65
     helicop
    -0.63
    cycl
    -0.62
     Centauri
    -0.61
    establishment
    -0.60
    POSITIVE LOGITS
    Laughs
    1.16
    laughs
    1.12
    laughter
    0.98
    laugh
    0.92
    HAEL
    0.84
    swers
    0.79
    ause
    0.78
    aughs
    0.77
    terness
    0.75
    creen
    0.74
    Act Density 0.016%

    No Known Activations