INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Mary
    -0.09
     Duch
    -0.09
     porcelain
    -0.08
    xm
    -0.08
     المسلحة
    -0.08
    Mary
    -0.08
     Exodus
    -0.08
     Sandra
    -0.08
    Christine
    -0.08
    Seal
    -0.08
    POSITIVE LOGITS
     habits
    0.13
     hábitos
    0.10
    0.10
     practices
    0.10
    0.09
    0.09
     habitudes
    0.09
     tendencies
    0.08
     hábito
    0.08
     Practices
    0.08
    Act Density 0.020%

    No Known Activations