INDEX
Explanations
statements expressing concern or emphasis on the importance of an issue
New Auto-Interp
Head Attr Weights
0:0.07
1:0.03
2:0.09
3:0.08
4:0.08
5:0.06
6:0.04
7:0.03
8:0.24
9:0.11
10:0.07
11:0.03
Negative Logits
dissolved
-1.19
expired
-1.17
collapsed
-1.15
Mons
-1.13
consumed
-1.13
expelled
-1.11
Hollow
-1.09
burned
-1.09
revoked
-1.08
expires
-1.08
POSITIVE LOGITS
��
1.32
enthusi
1.25
Push
1.17
_>
1.16
tone
1.15
ِ
1.13
sentiments
1.13
itivity
1.12
Requ
1.12
Border
1.11
Activations Density 0.008%