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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing disapproval or strong criticism

    oai_token-act-pair · gpt-3.5-turbo

    words associated with expressions of disapproval or condemnation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.88
     Solitaire
    -0.73
    negie
    -0.69
    hack
    -0.68
    nown
    -0.67
     Wonders
    -0.67
    soDeliveryDate
    -0.67
    ovember
    -0.66
    weeney
    -0.66
    rentice
    -0.65
    POSITIVE LOGITS
     condemn
    0.92
     condemning
    0.84
     condemns
    0.77
    urous
    0.75
     condemnation
    0.74
     homophobic
    0.70
     denounce
    0.70
     denouncing
    0.69
     unres
    0.69
     harshly
    0.69
    Act Density 0.042%

    No Known Activations