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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and quotation marks indicating dialogue or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢŀ
    -0.28
     (“
    -0.26
     “
    -0.24
     “âĢ¦
    -0.21
    =”
    -0.20
     “[
    -0.20
     ``
    -0.19
    ,“
    -0.19
     """.
    -0.17
    ''.
    -0.17
    POSITIVE LOGITS
    ()"↵
    0.17
    "↵↵
    0.15
    âĢº
    0.15
     `
    0.14
    /fw
    0.14
    rodu
    0.14
    ."↵↵
    0.14
    UTE
    0.14
    ()"
    0.13
    bove
    0.13
    Act Density 0.278%

    No Known Activations