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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific characters used in language structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     a
    -0.64
    <bos>
    -0.61
     the
    -0.60
     #
    -0.58
    ITECT
    -0.55
    ItemClick
    -0.55
     Tan
    -0.54
     Smith
    -0.54
     onStart
    -0.53
     an
    -0.53
    POSITIVE LOGITS
    出版年
    1.04
    ；
    0.98
    ：
    0.97
     ſever
    0.94
    ．
    0.94
     enfans
    0.92
     myſelf
    0.88
    )：
    0.86
    ）
    0.86
     pouvoit
    0.85
    Act Density 0.086%

    No Known Activations