INDEX
    Explanations

    mentions of political figures, specifically British politicians

    New Auto-Interp
    Negative Logits
    üzel
    -0.16
    æ°¸ä¹ħ
    -0.15
    _dot
    -0.15
    åı
    -0.15
    ово
    -0.15
    lain
    -0.15
    odb
    -0.14
    odic
    -0.14
    ãĤ«ãĥ¼
    -0.14
     EntityState
    -0.14
    POSITIVE LOGITS
    hti
    0.15
    Ïĩε
    0.15
     poll
    0.15
    vang
    0.14
    CHEDULE
    0.14
     skate
    0.14
    acio
    0.14
    anova
    0.13
    åŃ
    0.13
    289
    0.13
    Act Density 0.002%

    No Known Activations