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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     cellpadding
    -0.49
    cer
    -0.48
     river
    -0.48
    ViewFeatures
    -0.48
    zer
    -0.48
     dich
    -0.47
    kuuta
    -0.47
    łoż
    -0.47
    ัย
    -0.47
    出版年
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.86
     للاسماء
    0.77
    \"");
    0.76
    ')));
    0.73
     CreateTagHelper
    0.72
     propOrder
    0.70
    المناصب
    0.68
     ")");
    0.68
    ]";
    0.66
    ")));
    0.66
    Act Density 0.003%

    No Known Activations