INDEX
    Explanations

    references to specific political figures, particularly Rahul Gandhi and Imran Khan

    New Auto-Interp
    Negative Logits
     Scotia
    -0.96
     Concord
    -0.96
    foundland
    -0.94
     Bucc
    -0.77
    ĨĴ
    -0.73
     Marketable
    -0.70
    apple
    -0.69
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    é¾įå¥ij士
    -0.68
     Sorceress
    -0.67
    POSITIVE LOGITS
     Rahul
    1.30
    Rah
    0.94
     Gandhi
    0.93
    igans
    0.92
     Sharma
    0.87
     Pradesh
    0.79
    enei
    0.78
    jit
    0.78
     lapt
    0.77
     Rah
    0.76
    Act Density 0.010%

    No Known Activations