INDEX
    Explanations

    question marks and phrases that indicate questioning or inquiry

    question marks followed by sentence endings

    New Auto-Interp
    Negative Logits
    blauch
    -0.46
    <h1>
    -0.43
    imedia
    -0.43
    <blockquote>
    -0.42
    MathML
    -0.41
     thiệu
    -0.41
    ]<<"
    -0.41
    zeigen
    -0.40
    DTD
    -0.39
    📛
    -0.39
    POSITIVE LOGITS
    %?
    1.17
    ?”
    1.16
    ?).
    1.14
    1.13
    ?"
    1.09
    ?’
    1.09
    ?'
    1.09
    ?";
    1.05
    ?");
    1.05
    ?}
    1.05
    Act Density 0.006%

    No Known Activations