INDEX
    Explanations

    references to concussions and related terminology

    New Auto-Interp
    Negative Logits
    ropa
    -0.16
    orial
    -0.15
    earing
    -0.15
    imal
    -0.15
    Animator
    -0.15
    .pub
    -0.15
    utto
    -0.14
    weit
    -0.14
    èo
    -0.14
    tings
    -0.14
    POSITIVE LOGITS
     conc
    0.21
    conc
    0.20
    озд
    0.18
     Conc
    0.18
    ise
    0.17
     Concord
    0.16
    ussion
    0.15
    ant
    0.15
     INLINE
    0.15
    enate
    0.15
    Act Density 0.020%

    No Known Activations