INDEX
    Explanations

    expressions of strong emotional responses or violent actions

    New Auto-Interp
    Negative Logits
     виправивши
    -0.58
     Wikimedijinoj
    -0.55
     disponibilités
    -0.54
     Hockey
    -0.53
    Portale
    -0.52
    IsMutable
    -0.51
     Ause
    -0.50
    Hockey
    -0.49
     diretto
    -0.49
     inappro
    -0.49
    POSITIVE LOGITS
     Theory
    0.59
    InitStruct
    0.54
    KommentareTeilen
    0.54
    новништво
    0.53
    ')['
    0.53
    Theory
    0.51
     Braun
    0.50
    ochet
    0.50
    emplace
    0.50
    NameInMap
    0.49
    Act Density 0.176%

    No Known Activations