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

    Neuronpedia

    INDEX
    Explanations

    instances of numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.83
    Interstitial
    -0.77
     Conditions
    -0.72
    osi
    -0.69
    INTON
    -0.68
    Accessory
    -0.68
    ¯¯
    -0.66
    lements
    -0.66
    OPLE
    -0.65
    nee
    -0.64
    POSITIVE LOGITS
    metry
    0.87
    pace
    0.84
    paces
    0.82
     Numbers
    0.80
     numbers
    0.80
    ynthesis
    0.78
    eah
    0.73
    peak
    0.71
    matic
    0.71
    poons
    0.71
    Act Density 0.026%

    No Known Activations