INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     история
    -0.08
     historie
    -0.08
    .are
    -0.07
     cosmic
    -0.07
     социаль
    -0.07
     rpt
    -0.07
     dips
    -0.07
    {}.
    -0.07
    Ê
    -0.07
    .Managed
    -0.07
    POSITIVE LOGITS
     forward
    0.11
     avanti
    0.11
     вперед
    0.10
    _FORWARD
    0.10
    _forward
    0.10
    一步
    0.09
     pace
    0.09
     Forward
    0.09
    Forward
    0.09
     adelante
    0.09
    Act Density 0.049%

    No Known Activations