INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    oot
    -0.07
    Dest
    -0.07
     기록
    -0.07
    öst
    -0.07
     شهرستان
    -0.07
    _Map
    -0.07
     уклад
    -0.07
    _DUMP
    -0.06
    .plot
    -0.06
    _node
    -0.06
    POSITIVE LOGITS
     TV
    0.15
    TV
    0.15
     television
    0.13
     tv
    0.11
     Television
    0.11
    levision
    0.10
    DTV
    0.10
     Tv
    0.10
    tv
    0.09
    -TV
    0.09
    Act Density 0.014%

    No Known Activations