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

    Neuronpedia

    INDEX
    Explanations

    ratings or rankings

    oai_token-act-pair · gpt-3.5-turbo

    numerical ratings and rankings of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibus
    -0.71
     impunity
    -0.68
    ipation
    -0.68
    ellar
    -0.67
     contact
    -0.63
    pat
    -0.60
    ĨĴ
    -0.60
    acas
    -0.60
    soever
    -0.59
    GREEN
    -0.58
    POSITIVE LOGITS
     percentile
    0.80
     Ratings
    0.80
    formance
    0.77
     Highest
    0.74
    geist
    0.74
     Enlight
    0.73
    eous
    0.71
    ocre
    0.71
    iculty
    0.69
     subjective
    0.69
    Act Density 0.262%

    No Known Activations