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

    Neuronpedia

    INDEX
    Explanations

    numbers with decimal points

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    raltar
    -0.65
    ilial
    -0.65
    ributed
    -0.59
    iesta
    -0.59
    linger
    -0.59
     marqu
    -0.59
     Dent
    -0.59
    parser
    -0.58
    redo
    -0.57
    rament
    -0.57
    POSITIVE LOGITS
     million
    1.07
    GHz
    1.04
     billion
    1.03
    %
    0.95
     trillion
    0.95
     crore
    0.92
     percent
    0.91
     ±
    0.88
    million
    0.86
     lakh
    0.86
    Act Density 0.066%

    No Known Activations