INDEX
Explanations
expressions of hospitality and warmth towards others
New Auto-Interp
Negative Logits
kop
-0.19
ivan
-0.16
xies
-0.15
igg
-0.15
ICA
-0.15
-Owned
-0.15
.dm
-0.14
ypad
-0.14
rene
-0.14
iem
-0.14
POSITIVE LOGITS
_GPIO
0.15
Hier
0.15
welcomes
0.14
welcome
0.14
719
0.14
((((
0.14
룸
0.14
dạng
0.14
/tos
0.13
hosp
0.13
Activations Density 0.194%