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

    Neuronpedia

    INDEX
    Explanations

    strings of characters that may represent a specific language or encoding

    oai_token-act-pair · gpt-3.5-turbo

    symbols and characters related to Asian languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     msec
    -0.82
    ftime
    -0.80
    ufact
    -0.75
    mination
    -0.72
     assemb
    -0.72
    nyder
    -0.72
    resso
    -0.71
    abase
    -0.71
    arton
    -0.70
    linger
    -0.69
    POSITIVE LOGITS
    ¥
    1.46
    Į
    1.34
    æĹ
    1.33
    æ
    1.31
    ı
    1.31
    ç
    1.31
    è
    1.30
    é
    1.30
    İ
    1.30
    çĶ
    1.30
    Act Density 0.014%

    No Known Activations