INDEX
Explanations
instances of emotional expression or statements about feelings
New Auto-Interp
Negative Logits
ascal
-0.15
%f
-0.15
fil
-0.14
ãĤ½ãĥ³
-0.13
ertino
-0.13
éĤ
-0.13
698
-0.13
Universal
-0.13
amma
-0.13
sed
-0.13
POSITIVE LOGITS
utr
0.17
icode
0.16
avir
0.14
.scalablytyped
0.14
िà¤ļ
0.14
stk
0.14
.Apis
0.14
Tall
0.14
wnd
0.14
achuset
0.14
Activations Density 0.113%