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

    Neuronpedia

    INDEX
    Explanations

    numbers representing large amounts or values

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts in billions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prompt
    -0.71
    ourn
    -0.66
     Stur
    -0.65
     Sakuya
    -0.62
    ette
    -0.62
    vale
    -0.61
    selection
    -0.60
     Ale
    -0.59
    aints
    -0.58
    ayson
    -0.58
    POSITIVE LOGITS
     billion
    3.43
     trillion
    2.66
    billion
    2.66
     Billion
    2.56
     billions
    2.29
     million
    2.09
     trillions
    2.00
    bn
    1.98
     crore
    1.77
    million
    1.63
    Act Density 0.021%

    No Known Activations