INDEX
    Explanations

    references to "thing" or "things" in various contexts

    New Auto-Interp
    Negative Logits
    iconCls
    -0.38
    Advoc
    -0.36
    fflush
    -0.36
     unmarked
    -0.35
     Hotspur
    -0.35
    Dziękuję
    -0.35
     curator
    -0.34
    static
    -0.34
     serez
    -0.34
    niversitesi
    -0.34
    POSITIVE LOGITS
     thing
    2.03
    thing
    1.88
     THING
    1.64
    Thing
    1.59
     Thing
    1.55
    THING
    1.46
     things
    1.46
     coisa
    1.39
    things
    1.38
     stuff
    1.35
    Act Density 0.170%

    No Known Activations