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

    Neuronpedia

    INDEX
    Explanations

    quantities or measurements of something

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATA
    -0.64
     mate
    -0.59
    Fly
    -0.59
    lish
    -0.59
    emis
    -0.58
    lock
    -0.57
    azz
    -0.56
    aze
    -0.56
    jet
    -0.55
    Track
    -0.55
    POSITIVE LOGITS
     amounts
    3.97
     quantities
    2.55
     amount
    2.34
     sums
    2.05
    amount
    1.98
     Amount
    1.75
     amounted
    1.67
    Amount
    1.66
     proportions
    1.64
     doses
    1.62
    Act Density 0.013%

    No Known Activations