INDEX
    Explanations

    future events and outcomes

    New Auto-Interp
    Negative Logits
    і
    1.09
    1.02
    ни
    1.00
    ме
    0.99
     œufs
    0.95
    ين
    0.93
    το
    0.90
     он
    0.90
     ότι
    0.89
    и
    0.87
    POSITIVE LOGITS
    (
    1.52
    t
    1.41
    P
    1.40
    ang
    1.39
    H
    1.38
    X
    1.38
    B
    1.37
    im
    1.30
    PM
    1.30
    W
    1.27
    Act Density 0.010%

    No Known Activations