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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /or
    -0.17
    ceso
    -0.15
    iction
    -0.15
    ãģįãģŁ
    -0.14
    款
    -0.14
    ocate
    -0.14
    ffc
    -0.14
    Liver
    -0.13
    olean
    -0.13
    oltip
    -0.13
    POSITIVE LOGITS
    ÂĿ
    0.24
    ed
    0.21
    s
    0.19
    nbsp
    0.19
    ../../../
    0.17
    ÛĮ
    0.16
    ़
    0.15
    ftware
    0.15
    el
    0.15
    d
    0.14
    Act Density 0.152%

    No Known Activations