INDEX
Explanations
the prefix "un" used in various contexts
New Auto-Interp
Negative Logits
Theſe
-1.18
ainfi
-1.16
MainAxisSize
-1.10
myſelf
-1.07
becauſe
-1.06
ſche
-1.01
metropolitana
-0.93
itſelf
-0.91
་་
-0.90
Beſ
-0.90
POSITIVE LOGITS
un
1.70
Un
1.68
Un
1.52
UN
1.36
un
1.33
UN
1.12
Pre
0.96
n
0.92
Re
0.91
pre
0.91
Activations Density 0.045%