INDEX
Explanations
references to user input prompts and commands
New Auto-Interp
Negative Logits
Houſe
-1.15
Efq
-1.15
―――――
-1.11
Eſ
-1.08
Diſ
-1.06
ſeveral
-1.02
whoſe
-1.02
myſelf
-1.01
Perſ
-1.00
Inſ
-1.00
POSITIVE LOGITS
\,\
0.79
\,
0.73
\,
0.72
0.72
enter
0.72
Enter
0.70
enter
0.67
Enter
0.64
0.64
Cheers
0.63
Activations Density 0.265%