INDEX
Explanations
sentence endings, punctuation
New Auto-Interp
Negative Logits
sprites
0.40
operands
0.38
straps
0.36
sacc
0.35
trillions
0.34
estrogens
0.34
valves
0.34
hashes
0.34
tachycardia
0.34
aphids
0.33
POSITIVE LOGITS
↵↵
0.48
↵
0.42
。
0.41
.
0.38
However
0.38
۔
0.37
Emphasis
0.35
።
0.35
Additionally
0.34
Various
0.34
Activations Density 3.513%