INDEX
Explanations
the word "while" in various contexts
New Auto-Interp
Negative Logits
Datuak
-1.01
SAK
-0.96
ALF
-0.91
Cæsar
-0.88
NSCoder
-0.87
Falk
-0.86
Lyt
-0.84
Kombat
-0.84
RPS
-0.83
Falk
-0.83
POSITIVE LOGITS
while
1.35
While
1.31
while
1.28
WHILE
1.25
WHILE
1.20
While
1.19
whilst
1.06
Mientras
1.03
Enquanto
1.02
Whilst
1.02
Activations Density 0.078%