INDEX
    Explanations

    words related to legal conviction and guilt

    New Auto-Interp
    Negative Logits
    aways
    -0.19
    ียร
    -0.15
    fü
    -0.15
    èĮ
    -0.15
    cki
    -0.14
    thon
    -0.14
    è¡ĵ
    -0.14
    ायत
    -0.14
    fact
    -0.14
    ":[{↵
    -0.14
    POSITIVE LOGITS
     of
    0.22
     Battlefield
    0.15
    ÄĻp
    0.15
     under
    0.15
     orchestr
    0.14
     participation
    0.14
     involvement
    0.14
     Et
    0.14
     Kou
    0.14
     based
    0.13
    Act Density 0.026%

    No Known Activations