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

    Neuronpedia

    INDEX
    Explanations

    percentages and probabilities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to probabilities and statistical chances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APTER
    -0.91
    æ©
    -0.85
    ibur
    -0.81
     annex
    -0.76
    ustomed
    -0.71
    iliary
    -0.70
     export
    -0.69
    edia
    -0.69
    atha
    -0.69
    PHOTOS
    -0.68
    POSITIVE LOGITS
     probability
    1.99
     probabilities
    1.89
     odds
    1.63
     likelihood
    1.57
    chance
    1.54
     chance
    1.47
     chances
    1.34
     improbable
    1.33
     Prob
    1.29
    lihood
    1.27
    Act Density 0.410%

    No Known Activations