INDEX
Explanations
specific names of people or entities within a political or environmental context
New Auto-Interp
Negative Logits
pun
-0.18
oram
-0.15
FORMATION
-0.14
-FIRST
-0.14
discrim
-0.14
punkt
-0.14
dwar
-0.13
ContentType
-0.13
cke
-0.13
иÑĤÑĥ
-0.13
POSITIVE LOGITS
ause
0.17
ató
0.15
sao
0.14
thy
0.14
/renderer
0.14
.ua
0.14
Cycle
0.14
365
0.13
winter
0.13
ults
0.13
Activations Density 0.011%