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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific conditions, such as physical states or settings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -1.21
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -1.17
    é¾įåĸļ士
    -1.04
    NESS
    -1.03
     Continued
    -1.03
    ãĥ´ãĤ¡
    -1.02
    gerald
    -1.01
    æ©Ł
    -0.95
    WARD
    -0.93
     Accountability
    -0.93
    POSITIVE LOGITS
    iddling
    1.88
    idd
    1.65
    umps
    1.63
    ichael
    1.63
    akings
    1.61
    ugg
    1.58
    ixed
    1.58
    umbling
    1.57
    oto
    1.56
    apping
    1.55
    Act Density 0.656%

    No Known Activations