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

    Neuronpedia

    INDEX
    Explanations

    actions or attitudes related to dismissing or downplaying something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to dismissive or indifferent reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peaks
    -0.69
    essions
    -0.67
     indu
    -0.66
    ovych
    -0.66
    RAW
    -0.63
     Keeper
    -0.63
    amine
    -0.62
     unfocusedRange
    -0.62
    enos
    -0.61
    enment
    -0.59
    POSITIVE LOGITS
     shrug
    1.11
     deflect
    0.95
     aside
    0.87
    acket
    0.79
    ãĤ©
    0.77
    ython
    0.75
    sheet
    0.71
    ball
    0.71
    ulent
    0.70
     Nil
    0.70
    Act Density 0.043%

    No Known Activations