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

    Neuronpedia

    INDEX
    Explanations

    superlatives and comparatives

    oai_token-act-pair · gpt-3.5-turbo

    superlative forms of adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bara
    -0.79
    isson
    -0.74
    krit
    -0.73
    kas
    -0.72
    chwitz
    -0.71
    paio
    -0.70
    aly
    -0.68
    dinand
    -0.67
    verett
    -0.67
    utm
    -0.67
    POSITIVE LOGITS
     imaginable
    1.02
     conceivable
    0.90
     possible
    0.84
    seller
    0.77
    ream
    0.74
    hest
    0.73
    anding
    0.73
     Wanted
    0.68
     ever
    0.68
    iaries
    0.67
    Act Density 0.024%

    No Known Activations