INDEX
Explanations
quantitative data and numerical statistics
New Auto-Interp
Negative Logits
emark
-0.18
reich
-0.17
Millions
-0.16
-billion
-0.16
ième
-0.14
301
-0.14
imedia
-0.14
iams
-0.14
Mill
-0.14
roat
-0.14
POSITIVE LOGITS
dozen
0.18
fewer
0.17
udev
0.16
times
0.16
VisualStyle
0.15
)NULL
0.14
epy
0.14
o
0.14
-fold
0.13
oo
0.13
Activations Density 0.057%