INDEX
Explanations
mentions of the word "Marquette" and its variations
New Auto-Interp
Negative Logits
akra
-0.16
ntag
-0.16
laden
-0.16
erus
-0.15
ignant
-0.14
anny
-0.14
hort
-0.14
ulis
-0.14
hoa
-0.14
ç£
-0.14
POSITIVE LOGITS
imli
0.16
beer
0.15
chers
0.15
patron
0.15
fo
0.15
609
0.14
biç
0.14
inson
0.14
ocab
0.14
ιÏİν
0.14
Activations Density 0.005%