INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    gestion
    -0.08
     poprzez
    -0.08
     Duty
    -0.08
     arrested
    -0.08
    activities
    -0.07
    army
    -0.07
     DSC
    -0.07
    /etc
    -0.07
    portfolio
    -0.07
    .point
    -0.07
    POSITIVE LOGITS
    _len
    0.09
    _lengths
    0.09
    _size
    0.08
    _length
    0.08
    _seg
    0.08
    _start
    0.08
    (seg
    0.08
     shap
    0.08
    Length
    0.08
    _sizes
    0.07
    Act Density 0.007%

    No Known Activations