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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edii
    -0.15
    PPER
    -0.15
    reesome
    -0.15
    ãģ¯ãģļ
    -0.14
    à¸Ńà¸ĩ
    -0.14
    enci
    -0.14
    leigh
    -0.14
    stå
    -0.14
    天åłĤ
    -0.14
    Ïģά
    -0.14
    POSITIVE LOGITS
     (
    0.18
     Conv
    0.17
     conv
    0.16
     straight
    0.15
     Abram
    0.15
     is
    0.14
     area
    0.14
     ag
    0.14
     Yue
    0.14
    iges
    0.14
    Act Density 0.055%

    No Known Activations