INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ба
    -0.08
     Wei
    -0.07
    .figure
    -0.07
    Sir
    -0.07
    -0.07
    irler
    -0.07
    OBJECT
    -0.06
    23
    -0.06
     neutr
    -0.06
     Δή
    -0.06
    POSITIVE LOGITS
     Gospel
    0.08
     gospel
    0.07
     slang
    0.07
    lap
    0.07
     ště
    0.07
     migrating
    0.06
     cine
    0.06
     Singer
    0.06
     Oprah
    0.06
     evangel
    0.06
    Act Density 0.014%

    No Known Activations