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

    Neuronpedia

    INDEX
    Explanations

    numbers representing large amounts, specifically in the trillions

    oai_token-act-pair · gpt-3.5-turbo

    references to large numerical values, specifically numbers in the trillions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶æ
    -0.81
    supp
    -0.70
    WARE
    -0.68
     Continued
    -0.68
    bable
    -0.68
    side
    -0.67
     Colo
    -0.66
    bred
    -0.65
    mentioned
    -0.65
    headers
    -0.64
    POSITIVE LOGITS
     trillion
    1.01
     dollars
    1.00
    igr
    0.91
    aire
    0.90
     dollar
    0.86
     trillions
    0.83
    abyte
    0.83
    undo
    0.82
    dollar
    0.81
    ulously
    0.78
    Act Density 0.007%

    No Known Activations