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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols typically associated with dialogue or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -1.26
    ]")]
    -1.17
    存于互联网档案馆
    -1.16
     ivelany
    -1.08
     ویکی‌پدیا
    -1.08
    +#+#
    -1.07
    دانشنامهٔ
    -1.04
     חיצוניים
    -1.03
     Efq
    -1.00
     المعيارى
    -0.99
    POSITIVE LOGITS
    （
    1.87
     （
    1.65
    　
    1.61
    ：
    1.58
    【
    1.56
    ；
    1.42
    「
    1.41
    ）
    1.41
    ”（
    1.41
    ，
    1.37
    Act Density 0.086%

    No Known Activations