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

    Neuronpedia

    INDEX
    Explanations

    references to groups or categories that include the word "all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¦ãĤ¹
    -0.16
    _firestore
    -0.15
    -kind
    -0.15
    agne
    -0.15
    agna
    -0.14
    اسÛĮÙĪÙĨ
    -0.13
    AGO
    -0.13
    ird
    -0.13
    αιο
    -0.13
    oyer
    -0.13
    POSITIVE LOGITS
     except
    0.20
     available
    0.18
    strar
    0.17
     currently
    0.17
    currently
    0.16
     remaining
    0.16
     trừ
    0.16
    aptors
    0.16
    anca
    0.16
     Except
    0.15
    Act Density 0.100%

    No Known Activations