INDEX
    Explanations

    references to historical events and social issues, particularly related to the Holocaust and animal treatment

    New Auto-Interp
    Negative Logits
    arton
    -0.16
    /resource
    -0.15
    esty
    -0.14
     Xem
    -0.14
    mbH
    -0.14
     Ebony
    -0.14
    bam
    -0.14
    ictor
    -0.13
     ebony
    -0.13
     und
    -0.13
    POSITIVE LOGITS
    [level
    0.15
    BuilderInterface
    0.14
    ceries
    0.14
    oley
    0.13
    º
    0.13
    itters
    0.13
    899
    0.13
    ufen
    0.13
     vig
    0.13
    adia
    0.13
    Act Density 0.040%

    No Known Activations