INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     by
    -1.20
     to
    -1.11
    Anche
    -1.09
     although
    -1.07
     but
    -1.07
     अगर
    -1.02
     usually
    -1.01
    Perché
    -1.00
    Quando
    -1.00
     it
    -0.97
    POSITIVE LOGITS
     prior
    3.02
     Prior
    2.45
    Prior
    2.31
    prior
    2.14
     previous
    1.92
     previously
    1.87
     vorher
    1.80
     zuvor
    1.69
     sebelumnya
    1.62
     earlier
    1.55
    Act Density 0.066%

    No Known Activations