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

    Neuronpedia

    INDEX
    Explanations

    special characters used as separators or indicators

    oai_token-act-pair · gpt-3.5-turbo

    repeated special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stock
    -0.70
    wise
    -0.66
     keeping
    -0.66
     cock
    -0.65
     catch
    -0.64
     Dian
    -0.62
     reads
    -0.62
     board
    -0.62
     saves
    -0.61
     Poker
    -0.61
    POSITIVE LOGITS
    »
    4.51
    º
    2.21
    ½
    1.87
    ¿
    1.86
    ¼
    1.85
    ´
    1.71
    ¹
    1.69
    ³
    1.68
    ¾
    1.65
    ¸
    1.65
    Act Density 0.015%

    No Known Activations