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

    Neuronpedia

    INDEX
    Explanations

    instances of laughter or laughter-related expressions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quare
    -0.16
    AIT
    -0.15
     Dash
    -0.14
    "go
    -0.14
    posable
    -0.14
    aux
    -0.14
    ÑĦекÑĤив
    -0.13
    aland
    -0.13
    ounced
    -0.13
    itis
    -0.13
    POSITIVE LOGITS
     pause
    0.22
     Pause
    0.20
    pause
    0.19
    Pause
    0.19
    _pause
    0.17
    atal
    0.17
    .pause
    0.17
    _PAUSE
    0.16
    омеÑĤ
    0.16
     cough
    0.15
    Act Density 0.010%

    No Known Activations