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

    Neuronpedia

    INDEX
    Explanations

    mentions of languages or their related aspects in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of language and its aspects, particularly in relation to Mandarin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romeda
    -0.92
    roxy
    -0.92
    kus
    -0.91
    oppable
    -0.83
    nuts
    -0.83
    ilon
    -0.82
    apego
    -0.82
    lein
    -0.80
    OHN
    -0.80
    ersen
    -0.77
    POSITIVE LOGITS
     spoken
    1.25
     proficiency
    1.16
     learners
    1.13
     interpreter
    1.08
     barrier
    1.03
     lear
    0.98
    language
    0.94
     immersion
    0.93
     flu
    0.92
     arts
    0.92
    Act Density 0.057%

    No Known Activations