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

    Neuronpedia

    INDEX
    Explanations

    instances where text mentions an excessive amount or intensity of something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    byn
    -0.86
    saf
    -0.83
    selves
    -0.82
    Ń·
    -0.81
    stead
    -0.79
    İĭ
    -0.77
    ands
    -0.77
    iversary
    -0.73
    psons
    -0.73
    sylv
    -0.73
    POSITIVE LOGITS
     emphasis
    0.92
     inconsistency
    0.86
     attention
    0.85
    inventoryQuantity
    0.82
     trouble
    0.82
     effort
    0.81
     hassle
    0.80
     hype
    0.79
     temptation
    0.78
     dmg
    0.76
    Act Density 10.640%

    No Known Activations