INDEX
    Explanations

    references to legal actions and human rights violations

    New Auto-Interp
    Negative Logits
    roke
    -0.18
    .generic
    -0.15
    äh
    -0.15
    TAIL
    -0.15
    aju
    -0.15
    erge
    -0.14
    pty
    -0.14
     Lange
    -0.14
    oxetine
    -0.13
    RAY
    -0.13
    POSITIVE LOGITS
     Revised
    0.15
     Lehr
    0.15
    865
    0.14
    lbrakk
    0.14
    -corner
    0.14
    oplast
    0.14
    oser
    0.13
     Guild
    0.13
    iver
    0.13
    bery
    0.13
    Act Density 0.064%

    No Known Activations