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

    Neuronpedia

    INDEX
    Explanations

    distances expressed in kilometers and miles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     notoriety
    -0.66
     commissions
    -0.59
     fame
    -0.56
     personalities
    -0.53
     accidents
    -0.53
     publicity
    -0.51
     losses
    -0.51
     fatalities
    -0.51
     Taxes
    -0.51
     scandals
    -0.50
    POSITIVE LOGITS
    enough
    0.79
    apest
    0.70
    alle
    0.66
    Ãł
    0.65
    ļéĨĴ
    0.64
    arest
    0.64
     "$:/
    0.61
    arer
    0.60
    Ô
    0.60
    л
    0.60
    Act Density 0.454%

    No Known Activations