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

    Neuronpedia

    INDEX
    Explanations

    expressions related to large sums of money

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     overcoming
    -0.61
     biology
    -0.59
     pesky
    -0.59
     thumbs
    -0.58
     epidem
    -0.58
     firsthand
    -0.55
     accomplished
    -0.55
     spr
    -0.54
     testing
    -0.54
     posing
    -0.54
    POSITIVE LOGITS
    50
    1.17
    00
    1.15
    75
    1.07
    Downloadha
    1.01
    99
    1.01
    95
    1.00
    80
    1.00
    70
    1.00
    -$
    0.95
    60
    0.95
    Act Density 0.043%

    No Known Activations