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

    Neuronpedia

    INDEX
    Explanations

    historical information related to specific events, locations, and prominent figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    Optional
    -0.70
    anus
    -0.69
    afety
    -0.68
    ãĤ¢ãĥ«
    -0.67
    ibe
    -0.66
    rack
    -0.65
    Appearance
    -0.64
    emption
    -0.64
    inki
    -0.63
    POSITIVE LOGITS
     successive
    0.97
     steadily
    0.77
     accumulated
    0.76
     since
    0.73
     countless
    0.69
     sporadic
    0.69
     however
    0.67
    since
    0.67
     whenever
    0.67
     dozens
    0.66
    Act Density 0.291%

    No Known Activations