INDEX
    Explanations

    words that appear immediately before sentence- or clause-ending punctuation (like periods, commas, or colons).

    New Auto-Interp
    Negative Logits
    लेखित
    0.41
    0.40
    <unused1886>
    0.40
    <unused2006>
    0.40
    timeout
    0.40
    <unused384>
    0.38
    <unused1917>
    0.38
    <unused385>
    0.38
    <unused1875>
    0.38
    <unused323>
    0.38
    POSITIVE LOGITS
    0.78
    ۔
    0.59
    ,
    0.57
    0.56
    0.55
    ،
    0.53
    ։
    0.52
    .
    0.52
    ;
    0.52
    0.52
    Act Density 0.170%

    No Known Activations