INDEX
Explanations
phrases related to immigration and asylum seekers
New Auto-Interp
Negative Logits
ichen
-0.15
prod
-0.14
ula
-0.14
uries
-0.14
ãģ£ãģ¡
-0.14
etta
-0.14
vacuum
-0.13
bay
-0.13
net
-0.13
roll
-0.13
POSITIVE LOGITS
overst
0.24
applied
0.23
apply
0.23
natural
0.22
immigr
0.22
APPLY
0.20
living
0.20
.apply
0.20
Apply
0.20
applying
0.20
Activations Density 0.059%