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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format of month-day-year

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and notable historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iners
    -0.71
    urg
    -0.67
    escal
    -0.65
     spice
    -0.65
     bulletin
    -0.64
     costs
    -0.61
     redress
    -0.60
     ripple
    -0.60
    uden
    -0.59
    rouse
    -0.58
    POSITIVE LOGITS
     Died
    0.99
    >)
    0.89
    '),
    0.88
    )[
    0.87
     Born
    0.85
    Born
    0.85
    )—
    0.83
    )'
    0.83
    )]
    0.82
    ').
    0.81
    Act Density 0.087%

    No Known Activations