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

    Neuronpedia

    INDEX
    Explanations

    references to large sums of money

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sne
    -0.66
     Redd
    -0.65
     deviation
    -0.63
     deviations
    -0.62
     Dare
    -0.61
     Colors
    -0.61
     breakout
    -0.60
     Beh
    -0.59
     boun
    -0.59
     Det
    -0.59
    POSITIVE LOGITS
    300
    1.31
    600
    1.29
    100
    1.27
    200
    1.25
    400
    1.23
    800
    1.23
    700
    1.22
    150
    1.22
    1000
    1.21
    4000
    1.19
    Act Density 0.047%

    No Known Activations