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

    Neuronpedia

    INDEX
    Explanations

    actions or statements that are disapproved or criticized by authorities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "condemned"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thora
    -0.93
    mology
    -0.80
    athering
    -0.77
    opic
    -0.76
    ovember
    -0.76
    omal
    -0.74
    ewater
    -0.72
    vati
    -0.71
    bernatorial
    -0.70
    cially
    -0.70
    POSITIVE LOGITS
     condemned
    1.09
     condemning
    0.86
     condem
    0.82
     condemns
    0.80
    utsche
    0.76
     Osc
    0.73
     condemn
    0.71
     denounced
    0.71
     Survivors
    0.68
     Skinner
    0.67
    Act Density 0.006%

    No Known Activations