INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     isagoo
    -0.11
     એની
    -0.10
     akiwa
    -0.10
     he's
    -0.09
     bekommt
    -0.09
     ҳис
    -0.09
    ٢٠
    -0.09
    He's
    -0.09
     алган
    -0.09
    They're
    -0.09
    POSITIVE LOGITS
     Do
    0.26
    Do
    0.24
    _do
    0.20
     do
    0.20
    .Do
    0.20
    _Do
    0.19
    	do
    0.19
    .do
    0.17
    do
    0.17
     Please
    0.17
    Act Density 0.011%

    No Known Activations