INDEX
Explanations
references to awards, recognitions, and achievements in sports or competitions
New Auto-Interp
Negative Logits
plevel
-0.15
/context
-0.15
-
-0.14
estone
-0.14
adf
-0.14
estli
-0.14
ekk
-0.14
Simpson
-0.14
(/
-0.13
bash
-0.13
POSITIVE LOGITS
201
0.31
199
0.25
202
0.23
198
0.23
200
0.23
197
0.20
196
0.19
195
0.17
369
0.16
Û²Û°Û±
0.14
Activations Density 0.058%