INDEX
Explanations
mentions of the name "Ford"
New Auto-Interp
Negative Logits
zers
-0.15
ÏĢÏĮ
-0.15
jar
-0.14
Ù
-0.14
ccione
-0.13
umont
-0.13
ÐĽÑĮвÑĸв
-0.13
pedia
-0.13
ecom
-0.13
etsk
-0.13
POSITIVE LOGITS
971
0.15
Ñĥже
0.14
ney
0.14
_CLIP
0.14
ypad
0.14
ITED
0.14
laps
0.14
صÙĪØ±Øª
0.14
pta
0.13
alian
0.13
Activations Density 0.005%