INDEX
    Explanations

    references to mortality and social justice issues

    New Auto-Interp
    Negative Logits
     regardless
    -0.23
     renown
    -0.18
     Regardless
    -0.17
     wich
    -0.16
    elen
    -0.16
     reputable
    -0.15
     wording
    -0.15
    ourg
    -0.15
     smoothed
    -0.15
    Regardless
    -0.15
    POSITIVE LOGITS
     till
    0.28
     Till
    0.25
     erst
    0.23
    Apart
    0.19
     suo
    0.19
     atleast
    0.18
     etiqu
    0.18
     Sunder
    0.18
     leh
    0.18
     compuls
    0.17
    Act Density 4.503%

    No Known Activations