INDEX
    Explanations

    mentions of political parties, technology, and personal opinions in text.

    Comments and opinions

    New Auto-Interp
    Negative Logits
     Мексичка
    -0.99
     Normdatei
    -0.88
    Pautan
    -0.84
    (@"%@",
    -0.82
    )}</
    -0.80
    []>(
    -0.79
    )";
    
    -0.79
    ]")]
    -0.78
    "}>
    -0.76
    "])
    
    -0.75
    POSITIVE LOGITS
     …
    0.67
     всё
    0.59
    Ещё
    0.58
     учё
    0.57
     Всё
    0.55
    Всё
    0.54
     ...
    0.54
     лёг
    0.54
     ..
    0.53
    ..
    0.52
    Act Density 12.779%

    No Known Activations