INDEX
Explanations
statements about social and environmental responsibility
New Auto-Interp
Negative Logits
ished
-0.17
baugh
-0.16
uli
-0.15
isson
-0.15
annis
-0.15
Bail
-0.15
zion
-0.15
APA
-0.14
acco
-0.14
kov
-0.14
POSITIVE LOGITS
least
0.27
least
0.24
Least
0.24
Least
0.24
aviest
0.20
reatest
0.18
most
0.18
_least
0.17
most
0.16
tiên
0.16
Activations Density 0.103%