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

    Neuronpedia

    INDEX
    Explanations

    numerical values or mentions of numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nee
    -0.92
    ossier
    -0.80
    clair
    -0.77
    POSE
    -0.76
    INTON
    -0.73
    erate
    -0.72
    ISSION
    -0.72
    rib
    -0.71
     Shroud
    -0.70
    Interstitial
    -0.70
    POSITIVE LOGITS
     numbers
    1.33
     Numbers
    1.09
     digits
    0.95
    number
    0.88
    Numbers
    0.86
     numer
    0.85
     percentages
    0.84
    mith
    0.83
     figures
    0.80
    umbers
    0.78
    Act Density 0.016%

    No Known Activations