INDEX
    Explanations

    gym and fitness activities

    New Auto-Interp
    Negative Logits
    p
    1.33
    is
    1.28
    de
    1.24
    as
    1.21
    an
    1.04
    can
    1.02
    of
    1.02
    a
    1.02
    z
    1.01
    us
    0.93
    POSITIVE LOGITS
     overtaking
    1.05
     ότι
    1.01
    нима
    0.95
     agribusiness
    0.94
    یش
    0.93
    اتی
    0.92
     at
    0.91
    εται
    0.89
    0
    0.89
    یس
    0.88
    Act Density 0.001%

    No Known Activations