INDEX
    Explanations

    phrases related to political entities, specifically to the Coalition party

    mentions of a specific political coalition

    New Auto-Interp
    Negative Logits
    eatures
    -0.82
    lycer
    -0.76
    things
    -0.74
    DonaldTrump
    -0.74
    heat
    -0.73
    */(
    -0.71
    outed
    -0.68
    ortmund
    -0.66
    iour
    -0.66
    agate
    -0.66
    POSITIVE LOGITS
     Provision
    0.93
    naire
    0.93
     Aven
    0.87
     Coalition
    0.69
     Against
    0.69
     Member
    0.67
    hedral
    0.67
    isma
    0.66
    aires
    0.66
     Ashton
    0.66
    Act Density 0.016%

    No Known Activations