INDEX
    Explanations

    clear hierarchydata centerswestern culturesno loading

    New Auto-Interp
    Negative Logits
     stared
    0.59
     stare
    0.55
     staring
    0.52
     smiled
    0.49
    EROS
    0.49
     is
    0.48
     for
    0.48
     isn
    0.48
     turner
    0.48
     then
    0.48
    POSITIVE LOGITS
     وتن
    0.48
    0.46
    zię
    0.45
    ్రీ
    0.43
    傳統
    0.42
    Democratic
    0.42
    กร
    0.42
    Vik
    0.42
     prijs
    0.41
    ),
    0.41
    Act Density 0.004%

    No Known Activations