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

    Neuronpedia

    INDEX
    Explanations

    specific years and dates

    oai_token-act-pair · gpt-3.5-turbo

    instances of dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.76
    ascript
    -0.70
    spread
    -0.68
    safety
    -0.64
    abad
    -0.64
    arians
    -0.63
    average
    -0.63
    abled
    -0.61
    namese
    -0.61
    stable
    -0.61
    POSITIVE LOGITS
     fray
    0.69
     anew
    0.69
    Ń·
    0.69
     Gerr
    0.67
    OIL
    0.67
     Gutenberg
    0.64
     earnest
    0.64
    uberty
    0.63
    CEPT
    0.63
    ...]
    0.62
    Act Density 0.208%

    No Known Activations