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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or terms related to people and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ³
    -0.88
     externalToEVAOnly
    -0.76
    cloth
    -0.75
    ords
    -0.75
    creen
    -0.73
    ÄŁ
    -0.73
    pmwiki
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    Ö¼
    -0.67
    POSITIVE LOGITS
    rily
    1.20
    uish
    1.00
    lia
    0.98
    sty
    0.94
    regor
    0.88
    lers
    0.87
    ling
    0.81
    lyn
    0.80
    irl
    0.79
    rowth
    0.78
    Act Density 0.070%

    No Known Activations