INDEX
    Explanations

    end punctuation and common words

    New Auto-Interp
    Negative Logits
    .
    3.10
    2.64
    ™.
    2.37
    2.36
    ®.
    2.28
    ۔
    2.14
    ‌.
    2.11
    2.06
    1.89
    ¹.
    1.88
    POSITIVE LOGITS
    :")
    1.22
    ?")
    1.15
    :");
    1.08
    ?!"
    1.06
    ...")
    0.97
    ?");
    0.97
     असून
    0.92
    :"))
    0.90
    \":
    0.89
    0.89
    Act Density 0.669%

    No Known Activations