INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    enna
    -0.06
    _genre
    -0.06
    Av
    -0.06
     surveillance
    -0.06
    _border
    -0.06
     PF
    -0.06
     leží
    -0.06
     ranging
    -0.06
    -bel
    -0.06
     originating
    -0.06
    POSITIVE LOGITS
    ouch
    0.07
    -touch
    0.07
     کامل
    0.07
     Challenge
    0.06
     أمر
    0.06
    ised
    0.06
    osex
    0.06
    .Files
    0.06
     total
    0.06
    .comments
    0.06
    Act Density 0.002%

    No Known Activations