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

    Neuronpedia

    INDEX
    Explanations

    pronouns, specifically "they," "them," and "their."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owa
    -0.18
     cords
    -0.15
    vé
    -0.15
    rol
    -0.14
    534
    -0.14
    imit
    -0.14
    iset
    -0.14
    ial
    -0.14
    935
    -0.14
    934
    -0.14
    POSITIVE LOGITS
    ابت
    0.16
    inerary
    0.15
    нÑıв
    0.14
    kel
    0.14
    Cancelable
    0.14
    ForResource
    0.14
    κÏģι
    0.14
    paces
    0.14
     Morm
    0.13
    SEL
    0.13
    Act Density 0.481%

    No Known Activations