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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    date and time formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ñ
    -0.93
    ò
    -0.93
    ortunately
    -0.90
    isSpecial
    -0.89
    Ý
    -0.86
    oreAnd
    -0.80
    ThumbnailImage
    -0.80
     practition
    -0.78
    ô
    -0.77
     pione
    -0.76
    POSITIVE LOGITS
    59
    1.41
    53
    1.40
    03
    1.39
    58
    1.38
    57
    1.38
    54
    1.38
    52
    1.37
    56
    1.37
    51
    1.36
    55
    1.36
    Act Density 0.033%

    No Known Activations