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

    Neuronpedia

    INDEX
    Explanations

    financial numbers and percentages

    oai_token-act-pair · gpt-3.5-turbo

    financial statistics and percentage changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     experiment
    -0.66
     proudly
    -0.63
     upkeep
    -0.61
     kosher
    -0.60
     painstaking
    -0.59
    agna
    -0.59
     Blessed
    -0.59
     shit
    -0.59
     meticulously
    -0.59
    Phot
    -0.58
    POSITIVE LOGITS
    %.
    0.75
    ãĥĩãĤ£
    0.72
    %).
    0.72
    bps
    0.67
    fif
    0.67
    mean
    0.67
     (âĪĴ
    0.67
    37
    0.66
    %),
    0.66
    fen
    0.65
    Act Density 0.413%

    No Known Activations