INDEX
Explanations
references to time or duration in the context of cultural or geographic narratives
New Auto-Interp
Negative Logits
ragaz
-0.18
incy
-0.15
udeau
-0.14
ntag
-0.14
rottle
-0.14
PLUGIN
-0.14
atisch
-0.14
CSI
-0.14
zial
-0.14
ceb
-0.14
POSITIVE LOGITS
vir
0.27
die
0.23
Die
0.21
ê
0.21
die
0.20
Die
0.20
sy
0.20
sw
0.18
Kons
0.17
oor
0.17
Activations Density 0.008%