INDEX
Explanations
the word "while" in various forms
New Auto-Interp
Negative Logits
Lyt
-0.88
SAK
-0.84
Roch
-0.81
Sak
-0.80
Sak
-0.80
Falk
-0.79
sett
-0.79
ecs
-0.78
Eff
-0.78
.*/
-0.78
POSITIVE LOGITS
while
1.98
while
1.87
WHILE
1.77
While
1.75
While
1.64
whilst
1.60
WHILE
1.59
Whilst
1.42
mientras
1.40
Whilst
1.39
Activations Density 0.079%