INDEX
Explanations
sentences ending in periods
sentence-ending punctuation marks
New Auto-Interp
Negative Logits
manif
-0.81
iqueness
-0.78
describ
-0.71
shutting
-0.70
defin
-0.70
myster
-0.68
scen
-0.68
suspic
-0.67
indifferent
-0.67
orderly
-0.67
POSITIVE LOGITS
Subscribe
1.11
Published
1.07
Follow
1.05
Accessed
1.02
<|endoftext|>
0.99
Copyright
0.98
Visit
0.95
Retrieved
0.93
Reprodu
0.93
Previously
0.93
Activations Density 0.146%