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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism or negativity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stupid" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AUT
    -0.95
    APH
    -0.80
     largeDownload
    -0.77
    cussion
    -0.71
    soType
    -0.70
    aver
    -0.70
    Reviewed
    -0.67
    akings
    -0.67
    apers
    -0.67
    ILA
    -0.66
    POSITIVE LOGITS
    nesses
    0.95
     stupid
    0.84
    ishly
    0.83
    ly
    0.83
    ulously
    0.81
    itude
    0.80
     enough
    0.79
     silly
    0.77
    gery
    0.76
    liest
    0.75
    Act Density 0.014%

    No Known Activations