INDEX
Explanations
mentions of the football team Arsenal
New Auto-Interp
Negative Logits
owler
-0.15
geh
-0.15
ogn
-0.14
em
-0.14
ombre
-0.14
illard
-0.13
gis
-0.13
swire
-0.13
yg
-0.13
forb
-0.13
POSITIVE LOGITS
deer
0.16
uster
0.16
eros
0.15
wand
0.15
rada
0.15
еÑĢо
0.15
presso
0.15
metics
0.14
metic
0.14
vey
0.14
Activations Density 0.004%