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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers, specifically those indicating a degree or percentage

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hess
    -0.65
    linger
    -0.64
    ilial
    -0.59
     disguise
    -0.59
    rament
    -0.55
     Shant
    -0.55
     Painter
    -0.54
    adobe
    -0.53
     Tycoon
    -0.53
    ãĥĦ
    -0.52
    POSITIVE LOGITS
     million
    1.26
     billion
    1.14
     lakh
    1.11
    million
    1.10
     percent
    1.07
    %.
    1.04
    %
    1.03
     trillion
    1.02
    %,
    1.01
     crore
    0.99
    Act Density 0.061%

    No Known Activations