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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations and significant terms in a geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INESS
    -0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    forth
    -0.68
    weight
    -0.67
    Versions
    -0.67
    IGHTS
    -0.66
    姫
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    ãģ®éŃĶ
    -0.64
    enegger
    -0.64
    POSITIVE LOGITS
    acity
    0.94
    ta
    0.88
    idian
    0.86
    va
    0.86
    enda
    0.85
    kun
    0.83
    edo
    0.82
    acan
    0.80
    inished
    0.78
    ky
    0.76
    Act Density 0.004%

    No Known Activations