INDEX
Explanations
phrases indicating time duration and periods
New Auto-Interp
Negative Logits
athe
-0.16
Hastings
-0.16
oman
-0.15
añ
-0.15
ected
-0.14
913
-0.14
330
-0.14
figcaption
-0.14
esis
-0.14
ewe
-0.14
POSITIVE LOGITS
407
0.17
RIPT
0.17
onder
0.17
æĸ
0.15
letic
0.14
ysize
0.14
.infinity
0.14
TRL
0.14
Jvm
0.14
ppv
0.14
Activations Density 0.071%