INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ගත්
    0.73
     dagegen
    0.72
    はある
    0.72
    																													
    0.70
     другое
    0.70
     başka
    0.67
    ልቅ
    0.65
    ફેદ
    0.64
    خرى
    0.63
     manc
    0.63
    POSITIVE LOGITS
     most
    4.35
     가장
    4.18
    最も
    4.14
    4.06
     सबसे
    3.92
     সবচেয়ে
    3.87
     সবচেয়ে
    3.78
    most
    3.78
    Most
    3.74
     Most
    3.68
    Act Density 1.669%

    No Known Activations