INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    hnten
    0.96
    downloader
    0.92
    пс
    0.90
    ούμε
    0.88
    International
    0.87
    international
    0.87
    past
    0.86
    ങ്ങൾക്ക്
    0.86
    0.85
    연구
    0.84
    POSITIVE LOGITS
     two
    1.45
     doubleheader
    1.45
     deux
    1.43
     Two
    1.35
     duas
    1.34
     three
    1.34
     zwei
    1.33
     twin
    1.31
     Three
    1.30
     quatro
    1.29
    Act Density 0.260%

    No Known Activations