INDEX
    Explanations

    mentions of news organizations and their programs

    New Auto-Interp
    Negative Logits
    🇶
    -0.42
    Kem
    -0.40
     Alb
    -0.40
    
    -0.40
    ener
    -0.38
     старости
    -0.38
    literature
    -0.38
     Kem
    -0.37
    altern
    -0.37
     CreateTagHelper
    -0.36
    POSITIVE LOGITS
    BBC
    0.65
     BBC
    0.65
     propOrder
    0.58
     bbc
    0.54
    bbc
    0.54
     Вікіпе
    0.52
    bewerken
    0.50
    twimg
    0.49
    rungsseite
    0.48
     ویکی‌پدیا
    0.48
    Act Density 0.079%

    No Known Activations