INDEX
Explanations
mentions of specific locations, particularly "Coventry" and "Bristol."
New Auto-Interp
Negative Logits
.scalablytyped
-0.17
glich
-0.17
idar
-0.16
ALAR
-0.16
itur
-0.15
oft
-0.15
vánÃŃ
-0.15
_ATOMIC
-0.15
ott
-0.14
ضة
-0.14
POSITIVE LOGITS
CTION
0.15
714
0.14
кÑĤ
0.14
uran
0.14
646
0.14
lod
0.14
uang
0.14
574
0.14
ry
0.13
uhan
0.13
Activations Density 0.002%