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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    repeating numerical values or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyd
    -0.85
    atem
    -0.82
    ãĤ¡
    -0.77
     Beckham
    -0.71
    ogue
    -0.69
    Ñĭ
    -0.67
    ensibly
    -0.64
    ation
    -0.64
    rid
    -0.62
    igating
    -0.62
    POSITIVE LOGITS
    teenth
    0.93
    08
    0.93
    393
    0.90
    06
    0.89
    92
    0.87
    07
    0.87
    04
    0.86
    09
    0.84
    th
    0.84
    00
    0.83
    Act Density 0.030%

    No Known Activations