INDEX
    Explanations

    speaker attribution after quote

    New Auto-Interp
    Negative Logits
     কথাটা
    0.58
     accusation
    0.58
    ですよ
    0.58
     muttered
    0.57
     argument
    0.56
     بقى
    0.55
     misspelled
    0.54
    0.54
    んじゃない
    0.53
    不高
    0.53
    POSITIVE LOGITS
     Additionally
    0.88
     می‌باشد
    0.87
     এছাড়াও
    0.83
     Также
    0.80
     또한
    0.79
     Explained
    0.79
     Somit
    0.79
    utilizzo
    0.77
    또한
    0.75
     더욱
    0.74
    Act Density 0.005%

    No Known Activations