INDEX
Explanations
mentions of the term "Mac."
New Auto-Interp
Negative Logits
zoll
-0.43
Garland
-0.41
Epic
-0.41
MARS
-0.38
生
-0.37
Lois
-0.37
Lois
-0.37
Minor
-0.37
MIA
-0.36
Pup
-0.36
POSITIVE LOGITS
Mac
2.33
mac
2.31
Mac
2.22
mac
2.17
Mc
2.08
macro
2.03
Мак
1.94
Mc
1.86
Mack
1.84
macro
1.81
Activations Density 0.233%