INDEX
    Explanations

    prepositions followed by articles or nouns

    New Auto-Interp
    Negative Logits
    rmse
    0.95
    ности
    0.86
    gments
    0.82
    rop
    0.81
    issue
    0.80
    t
    0.79
    ierrez
    0.79
    in
    0.78
    ec
    0.77
    ری
    0.77
    POSITIVE LOGITS
     laquelle
    0.98
     stellte
    0.98
     VB
    0.96
     kojoj
    0.94
     blanches
    0.89
     vulgaris
    0.87
     funkcji
    0.87
     يسم
    0.86
     lequel
    0.86
    もの
    0.85
    Act Density 0.247%

    No Known Activations