INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     indicated
    -1.69
    indicated
    -1.48
     suggested
    -1.46
    suggested
    -1.30
     demonstrated
    -1.23
     indiqué
    -1.23
     confirmed
    -1.19
     Suggested
    -1.18
     stated
    -1.14
     implied
    -1.12
    POSITIVE LOGITS
     the
    0.93
     a
    0.82
     that
    0.70
     an
    0.66
    ly
    0.64
     another
    0.63
    +#+
    0.63
     something
    0.60
     his
    0.59
     some
    0.58
    Act Density 0.042%

    No Known Activations