INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.09
    -0.09
     квартир
    -0.08
     Respir
    -0.08
     despe
    -0.08
    -0.08
     Francesco
    -0.08
     наг
    -0.08
     Lug
    -0.07
    wreck
    -0.07
    POSITIVE LOGITS
    -spectrum
    0.11
     broadband
    0.08
     spectrum
    0.08
     foster
    0.07
    BG
    0.07
     construed
    0.07
     Beth
    0.07
     broaden
    0.07
     assimilation
    0.07
    0.07
    Act Density 0.008%

    No Known Activations