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

    Neuronpedia

    INDEX
    Explanations

    financial figures, such as amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propriet
    -0.69
     absor
    -0.69
     sooner
    -0.68
     corrections
    -0.68
     authority
    -0.64
     derog
    -0.64
     adherence
    -0.64
     disp
    -0.63
     revision
    -0.63
     deviations
    -0.63
    POSITIVE LOGITS
    150
    1.46
    350
    1.42
    250
    1.41
    100
    1.41
    750
    1.33
    400
    1.33
    300
    1.33
    675
    1.31
    200
    1.30
    500
    1.30
    Act Density 0.070%

    No Known Activations