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

    Neuronpedia

    INDEX
    Explanations

    specific numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "number" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -0.88
    Interstitial
    -0.76
     Shroud
    -0.74
    outer
    -0.73
    Materials
    -0.72
    axter
    -0.71
    INTON
    -0.69
    IAL
    -0.67
    Sov
    -0.66
    romeda
    -0.65
    POSITIVE LOGITS
    plates
    0.95
    enance
    0.79
     crunch
    0.76
    number
    0.76
    esses
    0.76
     999
    0.74
     digits
    0.74
     number
    0.73
    plate
    0.73
    ãĥ¼ãĥ³
    0.72
    Act Density 0.041%

    No Known Activations