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

    Neuronpedia

    INDEX
    Explanations

    numerical values such as measurements and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "$:/
    -0.72
    auder
    -0.68
    assic
    -0.64
    anan
    -0.63
    ouver
    -0.62
    inois
    -0.62
    gypt
    -0.61
     struggle
    -0.59
    achus
    -0.59
     Humph
    -0.59
    POSITIVE LOGITS
    dden
    0.79
    200000
    0.71
    ffff
    0.66
    pixel
    0.66
    cycles
    0.62
    FFFF
    0.62
    000000
    0.61
    VALUE
    0.61
     HRC
    0.61
    rocket
    0.61
    Act Density 0.091%

    No Known Activations