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

    Neuronpedia

    INDEX
    Explanations

    references to extremely large financial figures or amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to large financial amounts, specifically in trillions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶æ
    -0.75
     ANGEL
    -0.71
    WARE
    -0.70
     SX
    -0.67
    bable
    -0.66
     Random
    -0.65
     Ars
    -0.65
    bred
    -0.64
    supp
    -0.64
     Expression
    -0.64
    POSITIVE LOGITS
     dollars
    1.07
     trillion
    0.95
    dollar
    0.93
    ulously
    0.87
    abyte
    0.85
     dollar
    0.85
    aire
    0.85
     trillions
    0.83
    undo
    0.82
    ython
    0.82
    Act Density 0.010%

    No Known Activations