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

    Neuronpedia

    INDEX
    Explanations

    the word "English" in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to the English language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prus
    -0.88
    onies
    -0.84
    apego
    -0.83
    aunder
    -0.83
    olls
    -0.81
    xtap
    -0.79
    igslist
    -0.79
    psy
    -0.78
    utic
    -0.76
    udeau
    -0.76
    POSITIVE LOGITS
     English
    1.07
     translation
    0.93
    English
    0.92
     translations
    0.90
    language
    0.85
     english
    0.83
    spe
    0.80
     Dictionary
    0.80
     Language
    0.79
     Portuguese
    0.79
    Act Density 0.019%

    No Known Activations