INDEX
Explanations
negative or critical sentiments conveyed through hyphenated or combined tokens
New Auto-Interp
Negative Logits
chtenstein
-0.70
in
-0.66
.
-0.66
,
-0.65
Varma
-0.60
verwaltung
-0.59
cioni
-0.58
ENNA
-0.58
רח
-0.57
of
-0.57
POSITIVE LOGITS
®-
1.34
′-
1.27
()-
1.26
*-
1.26
-
1.22
'-
1.22
&-
1.19
!-
1.16
disambiguazione
1.16
‐
1.14
Activations Density 1.235%