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

    Neuronpedia

    INDEX
    Explanations

    references to the term "language" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mitar
    -0.87
     Supremo
    -0.86
     Thine
    -0.80
    :✨
    -0.79
     himſelf
    -0.79
     fubject
    -0.76
     miſ
    -0.76
    améli
    -0.75
     Italij
    -0.75
     greateſt
    -0.74
    POSITIVE LOGITS
     languages
    1.31
     language
    1.22
     Language
    1.19
    Languages
    1.16
    Language
    1.13
     Languages
    1.10
    languages
    1.07
     Lang
    1.04
    Langue
    1.04
     LANG
    1.03
    Act Density 0.081%

    No Known Activations