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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or unique characters from various languages or texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    人类
    -0.16
    urs
    -0.15
    па
    -0.15
    ä¸Ģ人
    -0.15
    人çļĦ
    -0.15
    人
    -0.14
    gal
    -0.14
    emann
    -0.14
    427
    -0.14
    UGH
    -0.14
    POSITIVE LOGITS
    ãģŁãĤģãģ®
    0.20
    itu
    0.16
    ÃŃž
    0.15
    ãģŁãĤģãģ«
    0.14
    olls
    0.14
    tatus
    0.14
     Registered
    0.14
    aklı
    0.14
    halb
    0.13
     Authorized
    0.13
    Act Density 0.017%

    No Known Activations