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

    Neuronpedia

    INDEX
    Explanations

    numbers in decimals

    oai_token-act-pair · gpt-3.5-turbo

    numerical values representing statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raltar
    -0.77
    busters
    -0.74
    pty
    -0.73
    ships
    -0.68
    rament
    -0.67
    adobe
    -0.65
    umbn
    -0.64
    nuts
    -0.62
    lished
    -0.62
    ributed
    -0.61
    POSITIVE LOGITS
    GHz
    0.97
     million
    0.88
     billion
    0.88
     GHz
    0.80
     crore
    0.80
    MW
    0.79
     ±
    0.79
     Million
    0.78
    66666666
    0.77
    million
    0.77
    Act Density 0.072%

    No Known Activations