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

    Neuronpedia

    INDEX
    Explanations

    numbered lists or rankings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gypt
    -0.91
    ãĥ¼ãĥĨãĤ£
    -0.83
    ãĥ¼ãĥĨ
    -0.79
    alam
    -0.73
    inem
    -0.67
    ucl
    -0.67
    姫
    -0.66
     Rabb
    -0.66
    Ļ½
    -0.63
    achus
    -0.63
    POSITIVE LOGITS
    onsense
    0.75
    brainer
    0.74
    Shift
    0.70
     WATCHED
    0.63
    0001
    0.62
    notice
    0.62
    Fake
    0.61
     whatsoever
    0.61
     Chomsky
    0.61
    Notice
    0.59
    Act Density 1.057%

    No Known Activations