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

    Neuronpedia

    INDEX
    Explanations

    superlatives related to size or importance

    oai_token-act-pair · gpt-3.5-turbo

    superlative terms related to size or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arth
    -0.83
    isson
    -0.78
    utton
    -0.72
     Mandal
    -0.72
    zinski
    -0.71
     Kuala
    -0.70
     Meadows
    -0.69
    icum
    -0.69
    indal
    -0.69
    ayne
    -0.68
    POSITIVE LOGITS
     superpower
    0.78
     largest
    0.71
    largest
    0.67
     thous
    0.67
     adversaries
    0.66
     industrial
    0.65
     fastest
    0.65
    igious
    0.64
     billionaires
    0.63
     newspaper
    0.62
    Act Density 0.155%

    No Known Activations