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

    Neuronpedia

    INDEX
    Explanations

    numbers in parentheses representing statistical data

    oai_token-act-pair · gpt-3.5-turbo

    statistical data or percentages in a survey context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mishand
    -0.66
    ĸļ
    -0.66
     printing
    -0.65
     smugg
    -0.64
     Chaos
    -0.64
     poaching
    -0.62
     mete
    -0.62
     tarn
    -0.62
     staging
    -0.62
     Relief
    -0.62
    POSITIVE LOGITS
    56
    1.35
    63
    1.31
    57
    1.31
    53
    1.30
    58
    1.27
    54
    1.27
    73
    1.27
    52
    1.27
    71
    1.26
    51
    1.26
    Act Density 0.066%

    No Known Activations