INDEX
Explanations
references to the letter "Z" in various contexts
New Auto-Interp
Negative Logits
purpoſe
-0.83
faſt
-0.80
myſelf
-0.77
ſeveral
-0.77
Beſ
-0.76
pleaſure
-0.76
SEGU
-0.75
Anſ
-0.74
wiſe
-0.74
་་
-0.74
POSITIVE LOGITS
Z
3.08
Z
2.70
z
2.00
getZ
1.53
З
1.42
Z
1.40
z
1.31
З
1.24
Zs
1.21
ز
1.19
Activations Density 0.088%