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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their distribution in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    СÐŀ
    -0.17
    ä¹ĭä¸Ģ
    -0.16
    æĪ
    -0.15
    ίνη
    -0.15
    ume
    -0.14
     æĹ
    -0.14
    aseline
    -0.14
    ERG
    -0.14
    én
    -0.14
    aket
    -0.14
    POSITIVE LOGITS
    orris
    0.15
    MMdd
    0.15
    led
    0.14
    ibur
    0.14
    groundColor
    0.13
    ãĥ¥ãĥ¼
    0.13
    ionage
    0.13
    /blog
    0.13
     WithEvents
    0.13
     #-
    0.13
    Act Density 0.006%

    No Known Activations