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

    Neuronpedia

    INDEX
    Explanations

    statistics and numerical values with percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and percentages related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hess
    -0.74
    erity
    -0.71
    achev
    -0.69
     Wilde
    -0.69
     Tycoon
    -0.68
    bilt
    -0.67
    ModLoader
    -0.67
    stri
    -0.66
    ihu
    -0.66
    redo
    -0.65
    POSITIVE LOGITS
     percent
    1.22
    %
    1.14
    %,
    1.09
    %;
    1.08
    %.
    1.07
     million
    0.91
     %
    0.91
     Percent
    0.91
    %)
    0.90
    percent
    0.89
    Act Density 0.075%

    No Known Activations