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

    Neuronpedia

    INDEX
    Explanations

    the word "uh" repeated several times with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disbelief or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.73
     Reborn
    -0.73
    BALL
    -0.70
     Painter
    -0.68
    uncture
    -0.67
    ersen
    -0.67
    chnology
    -0.66
    女
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.62
    ertodd
    -0.61
    POSITIVE LOGITS
    ahah
    1.15
    awk
    1.03
    ansen
    0.96
    awks
    0.95
    ospital
    0.95
    undai
    0.92
    hhhh
    0.90
    annah
    0.87
    arsh
    0.83
    hh
    0.82
    Act Density 0.015%

    No Known Activations