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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format of day-month-year

    oai_token-act-pair · gpt-3.5-turbo

    the specific date "March 27."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urated
    -0.84
    ablishment
    -0.73
    yles
    -0.73
    imore
    -0.73
    aleb
    -0.71
    iple
    -0.71
    obic
    -0.71
    inction
    -0.70
    ensed
    -0.70
    opsy
    -0.69
    POSITIVE LOGITS
    00
    1.00
    th
    0.93
    27
    0.93
    rd
    0.92
    87
    0.85
    37
    0.84
    71
    0.83
    07
    0.82
    017
    0.82
    31
    0.82
    Act Density 0.019%

    No Known Activations