INDEX
    Explanations

    directional movement or orientation

    New Auto-Interp
    Negative Logits
    iejęt
    0.43
     salaried
    0.41
    頑張
    0.40
    0.40
    0.40
     katal
    0.39
    नोई
    0.39
    ทยาลัย
    0.39
    มาชิก
    0.39
    0.39
    POSITIVE LOGITS
     sideways
    0.99
     horizontally
    0.97
     towards
    0.96
     inward
    0.94
     laterally
    0.93
     toward
    0.91
     inwards
    0.91
     diagonally
    0.91
     tilted
    0.89
     hacia
    0.88
    Act Density 0.102%

    No Known Activations