INDEX
    Explanations

    terms related to evacuation and displacement due to emergencies

    New Auto-Interp
    Negative Logits
    hek
    -0.15
    -divider
    -0.15
    anium
    -0.14
    تاÙĨ
    -0.14
    inality
    -0.14
     overhead
    -0.14
    yb
    -0.14
    âĶIJ
    -0.14
    -upper
    -0.14
    classname
    -0.14
    POSITIVE LOGITS
    ord
    0.17
    ixe
    0.15
    ibel
    0.15
     reversed
    0.14
    ordin
    0.14
     slight
    0.14
    azi
    0.14
    inverse
    0.14
    keh
    0.14
    šť
    0.14
    Act Density 0.010%

    No Known Activations