INDEX
Explanations
references to travel and tourism activities
New Auto-Interp
Negative Logits
1
-0.82
↵
-0.67
↵↵
-0.57
2
-0.57
-0.57
6
-0.54
3
-0.52
5
-0.52
4
-0.51
-
-0.49
POSITIVE LOGITS
autorytatywna
1.48
müſſen
1.42
нгред
1.41
laſſen
1.36
ſeinen
1.36
verſch
1.35
majánló
1.35
Geſch
1.35
dieſen
1.34
<unused43>
1.33
Activations Density 1.316%