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

    Neuronpedia

    INDEX
    Explanations

    references to legal issues or violations related to politics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cerberus
    -0.82
     pony
    -0.77
     Ribbon
    -0.75
     Pegasus
    -0.72
     Strip
    -0.72
     Highlander
    -0.72
     Slayer
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    ĸļ
    -0.68
     Polo
    -0.67
    POSITIVE LOGITS
    resa
    1.07
    earing
    1.04
    ogether
    1.01
    ensing
    1.00
    etting
    1.00
    ounding
    0.98
    avin
    0.98
    ucci
    0.97
    ert
    0.93
    irt
    0.91
    Act Density 0.196%

    No Known Activations