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

    Neuronpedia

    INDEX
    Explanations

    articles and determiners in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "a" followed by adjective/noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.72
    :✨
    -0.72
    ðsíða
    -0.68
    verifyException
    -0.67
     ujednoznacz
    -0.67
    StructEnd
    -0.65
     ویکی‌پدی
    -0.64
     iconFacebook
    -0.63
     lenker
    -0.63
    VYMaps
    -0.63
    POSITIVE LOGITS
     Daß
    0.29
     ModelExpression
    0.28
     …
    0.27
    that
    0.27
    “
    0.27
     “
    0.27
     "
    0.26
     all
    0.26
     nobody
    0.25
    </strong>
    0.25
    Act Density 0.034%

    No Known Activations