INDEX
Explanations
expressions of concern and discussion about social and health issues in a specific context
New Auto-Interp
Negative Logits
coloured
-0.16
(*((
-0.16
BorderColor
-0.15
iren
-0.15
Ñģвое
-0.14
udeau
-0.14
iliz
-0.14
egree
-0.14
ILLS
-0.14
colours
-0.13
POSITIVE LOGITS
iate
0.15
Hans
0.15
.Compose
0.14
jian
0.14
è½
0.14
ient
0.13
lando
0.13
šku
0.13
.xy
0.13
Ī
0.13
Activations Density 0.029%