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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of day-month-year

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical information in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.81
    hower
    -0.69
    orem
    -0.69
    otine
    -0.67
    rored
    -0.63
     derailed
    -0.58
    anamo
    -0.57
    vre
    -0.57
    atically
    -0.57
    plin
    -0.56
    POSITIVE LOGITS
     October
    1.40
     February
    1.39
     September
    1.39
     July
    1.37
     June
    1.36
     November
    1.36
     April
    1.35
     January
    1.35
     August
    1.34
     December
    1.34
    Act Density 0.057%

    No Known Activations