INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    5
    1.27
    4
    1.27
    ка
    1.10
    0
    1.09
    6
    1.05
    2
    0.91
    3
    0.89
    0.86
    0.85
    ту
    0.80
    POSITIVE LOGITS
     on
    0.82
    tting
    0.67
     It
    0.64
    υτό
    0.61
    ਾਈ
    0.59
     Plants
    0.58
    aways
    0.58
     up
    0.57
    alers
    0.57
    0.57
    Act Density 5.043%

    No Known Activations