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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and names related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĽ£
    -0.17
    stÃŃ
    -0.17
    swire
    -0.15
    BOSE
    -0.14
    (Collision
    -0.14
    ulaire
    -0.14
    ابع
    -0.14
    adil
    -0.14
    AMESPACE
    -0.14
    oint
    -0.14
    POSITIVE LOGITS
     PEN
    0.17
     dens
    0.15
    iken
    0.15
    OUNCE
    0.15
    alen
    0.15
     Pen
    0.14
    nen
    0.14
    ÃŁen
    0.14
    Navigator
    0.14
     pen
    0.14
    Act Density 0.109%

    No Known Activations