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

    Neuronpedia

    INDEX
    Explanations

    numbers with a specific format, specifically the number 15

    oai_token-act-pair · gpt-3.5-turbo

    numeric values representing ages or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.84
    abwe
    -0.76
    qqa
    -0.75
    atem
    -0.73
    plom
    -0.73
    anamo
    -0.68
    EStream
    -0.68
    ipment
    -0.68
    ilic
    -0.68
    ramid
    -0.67
    POSITIVE LOGITS
    th
    1.13
    teenth
    0.95
    %"
    0.95
     stitches
    0.92
    ½
    0.87
    %,
    0.87
    81
    0.85
    %
    0.84
    87
    0.84
    71
    0.83
    Act Density 0.277%

    No Known Activations