INDEX
    Explanations

    terms related to historical movements or groups associated with notable ideological shifts

    New Auto-Interp
    Negative Logits
    ween
    -0.17
    oner
    -0.15
     Mash
    -0.15
    ä¿Ĭ
    -0.15
    ابط
    -0.14
    岸
    -0.14
    ĽĦ
    -0.14
    ony
    -0.14
     æķ
    -0.13
    ÙĦاÙĦ
    -0.13
    POSITIVE LOGITS
    kv
    0.15
    elsey
    0.14
    strand
    0.14
     Cylinder
    0.14
     |--------------------------------------------------------------------------↵
    0.14
    istro
    0.14
    -prepend
    0.14
    quis
    0.14
    /bower
    0.14
    stras
    0.13
    Act Density 0.075%

    No Known Activations