INDEX
    Explanations

    references to political parties and movements

    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĢ
    -0.19
    sert
    -0.15
     Blitz
    -0.14
     Gh
    -0.14
    uisine
    -0.14
    icode
    -0.14
    elta
    -0.14
    å±¥
    -0.14
    otics
    -0.14
    ella
    -0.13
    POSITIVE LOGITS
     aks
    0.14
    inded
    0.14
     Atlantic
    0.14
    BaseContext
    0.14
     Hicks
    0.14
    asaki
    0.14
     Siz
    0.14
    odega
    0.14
    elper
    0.14
     mileage
    0.13
    Act Density 0.010%

    No Known Activations