INDEX
    Explanations

    references to television or media terminology, particularly in relation to news and sports

    New Auto-Interp
    Negative Logits
    -0.32
    ļu
    -0.30
     detalhe
    -0.30
     těch
    -0.29
     detaylı
    -0.28
    seido
    -0.28
    ļi
    -0.28
     tratado
    -0.27
    <h2>
    -0.27
    ļa
    -0.27
    POSITIVE LOGITS
     Sky
    1.10
    Sky
    1.04
     SKY
    1.03
     sky
    1.02
     skys
    0.84
    SKY
    0.82
     Skies
    0.79
     Skys
    0.76
    sky
    0.75
     skies
    0.75
    Act Density 0.008%

    No Known Activations