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

    Neuronpedia

    INDEX
    Explanations

    dates represented as numbers

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.73
    urus
    -0.70
    players
    -0.67
    ayers
    -0.67
    paralle
    -0.66
    retty
    -0.64
     whilst
    -0.64
    ometers
    -0.63
    doing
    -0.63
    atown
    -0.63
    POSITIVE LOGITS
     deadline
    1.12
     edition
    1.10
     expiration
    1.09
     announcement
    0.97
     arrival
    0.93
     installment
    0.90
     inauguration
    0.88
     appointment
    0.87
    th
    0.86
     eruption
    0.86
    Act Density 0.065%

    No Known Activations