INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     команди
    1.14
     careless
    1.12
    िंग
    1.07
    ية
    1.06
    டி
    1.03
     sloppy
    1.00
    <!--
    0.99
    universe
    0.99
     équipes
    0.98
    𝚍
    0.97
    POSITIVE LOGITS
    tile
    1.04
    ciam
    1.02
     vệ
    1.00
    cen
    0.99
    rons
    0.98
    cere
    0.96
     nourrice
    0.95
    tran
    0.95
    z
    0.94
    البه
    0.93
    Act Density 0.000%

    No Known Activations