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

    Neuronpedia

    INDEX
    Explanations

    numbers or numerical patterns, specifically those indicating a specific value or statistic

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.78
     Flavoring
    -0.69
    ¥µ
    -0.64
    raltar
    -0.61
     Parade
    -0.61
    ourke
    -0.60
    ilant
    -0.59
    ions
    -0.59
    encers
    -0.59
     streamed
    -0.59
    POSITIVE LOGITS
    00
    0.88
    ielding
    0.81
    mares
    0.75
    50
    0.71
    wagen
    0.71
    hof
    0.71
    eenth
    0.70
    atural
    0.70
    ield
    0.69
    itely
    0.69
    Act Density 0.032%

    No Known Activations