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

    Neuronpedia

    INDEX
    Explanations

    references to language proficiency and multilingual abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     language
    -0.32
     Language
    -0.29
    -Language
    -0.29
     linguistic
    -0.28
    -language
    -0.28
    language
    -0.27
    /language
    -0.27
    è¯Ńè¨Ģ
    -0.25
    Language
    -0.24
     Lingu
    -0.24
    POSITIVE LOGITS
     convers
    0.20
     Basic
    0.19
     broken
    0.17
     Platt
    0.17
     Haus
    0.17
    -basic
    0.17
    iosk
    0.17
    Basic
    0.16
     mand
    0.16
    .basic
    0.16
    Act Density 0.080%

    No Known Activations