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

    Neuronpedia

    INDEX
    Explanations

    large quantities and monetary values

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical monetary values or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.70
    iths
    -0.64
     Friendly
    -0.62
    mates
    -0.62
    riter
    -0.58
    iannopoulos
    -0.57
    hib
    -0.55
     Niet
    -0.54
    emy
    -0.54
    lishes
    -0.52
    POSITIVE LOGITS
     worth
    1.31
     invested
    1.10
     (£
    1.05
     dollars
    1.02
     spent
    1.00
     expended
    0.98
     wasted
    0.96
     owed
    0.95
    -$
    0.92
     USD
    0.92
    Act Density 0.131%

    No Known Activations