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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "One" followed by a number, with a higher activation for occurrences of "One" followed by the number 9

    oai_token-act-pair · gpt-3.5-turbo

    references to the "One" product series, specifically related to mobile and gaming devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.79
    ãĤ¡
    -0.77
    lishes
    -0.75
    gomery
    -0.71
    urat
    -0.71
    ãĤ°
    -0.70
    len
    -0.68
    ruary
    -0.68
    apons
    -0.68
     srf
    -0.67
    POSITIVE LOGITS
     Hundred
    0.97
     Thousand
    0.86
     hundred
    0.81
     Million
    0.77
     dimensional
    0.75
     Month
    0.71
     Year
    0.70
     Piece
    0.70
     Hots
    0.69
     thousand
    0.69
    Act Density 0.034%

    No Known Activations