INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     transporter
    -0.07
    .cd
    -0.07
     splits
    -0.06
     scarc
    -0.06
    _fac
    -0.06
     languages
    -0.06
    departureday
    -0.06
     shipped
    -0.06
    _contains
    -0.06
    \d
    -0.06
    POSITIVE LOGITS
    mir
    0.08
     additions
    0.07
    xA
    0.07
    Khi
    0.06
     Khi
    0.06
     continual
    0.06
    _supp
    0.06
     така
    0.06
     ساعت
    0.06
     youthful
    0.06
    Act Density 0.005%

    No Known Activations