INDEX
    Explanations

    quantifiers before items

    New Auto-Interp
    Negative Logits
     materials
    -0.96
     drzwi
    -0.95
    逃げ
    -0.88
     flechas
    -0.84
     продукции
    -0.84
     veicolo
    -0.83
     posibilidades
    -0.82
     matériel
    -0.82
     Publikum
    -0.81
     solches
    -0.81
    POSITIVE LOGITS
     loaf
    1.73
     pair
    1.73
     bottle
    1.39
    pair
    1.24
     packet
    1.19
     dozen
    1.14
     pairs
    1.07
     batch
    1.05
     sets
    0.98
     gallon
    0.98
    Act Density 0.055%

    No Known Activations