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

    Neuronpedia

    INDEX
    Explanations

    words related to languages

    oai_token-act-pair · gpt-3.5-turbo

    mention of languages and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.92
    ilon
    -0.90
    oppable
    -0.85
    roxy
    -0.83
    roleum
    -0.82
    romeda
    -0.81
    apego
    -0.80
    urion
    -0.80
    iary
    -0.76
    rodu
    -0.76
    POSITIVE LOGITS
     spoken
    1.20
     learners
    1.13
     interpreter
    1.07
    language
    1.02
     proficiency
    1.01
     flu
    0.97
     translation
    0.93
    ĨĴ
    0.90
     immersion
    0.90
     languages
    0.89
    Act Density 0.054%

    No Known Activations