INDEX
Explanations
references to migrants and their related challenges
New Auto-Interp
Negative Logits
Interracial
-0.16
grams
-0.16
rieving
-0.15
ollen
-0.15
decorators
-0.15
arget
-0.14
gfx
-0.14
obby
-0.14
kas
-0.14
orns
-0.13
POSITIVE LOGITS
Border
0.30
border
0.29
asylum
0.28
caravan
0.27
crossings
0.27
Central
0.26
Border
0.25
illegal
0.25
migrants
0.25
illeg
0.24
Activations Density 0.018%