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

    Neuronpedia

    INDEX
    Explanations

    dates and deadlines mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" followed by a date

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rors
    -0.68
     encount
    -0.68
     spared
    -0.66
    ror
    -0.66
    ŃĶ
    -0.65
    acan
    -0.65
    inventoryQuantity
    -0.64
    plin
    -0.63
     multiplied
    -0.62
     oun
    -0.61
    POSITIVE LOGITS
     October
    1.29
     September
    1.28
     Sept
    1.27
     July
    1.27
     June
    1.25
     November
    1.24
     August
    1.23
     April
    1.23
     December
    1.23
     January
    1.22
    Act Density 0.104%

    No Known Activations