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

    Neuronpedia

    INDEX
    Explanations

    mentions of the number of languages a person knows

    oai_token-act-pair · gpt-3.5-turbo

    references to languages and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.87
    roxy
    -0.86
    ecake
    -0.84
    ilts
    -0.82
    apego
    -0.82
    oppable
    -0.81
    roleum
    -0.81
    arranted
    -0.78
    ilon
    -0.78
    rodu
    -0.78
    POSITIVE LOGITS
     spoken
    1.07
     learners
    0.98
    language
    0.95
     proficiency
    0.94
    ĨĴ
    0.94
     flu
    0.93
     interpreter
    0.90
     languages
    0.89
     translation
    0.87
     Languages
    0.84
    Act Density 0.035%

    No Known Activations