INDEX
Explanations
the word "you" in different contexts and settings
instances of the pronoun "you."
New Auto-Interp
Negative Logits
Reviewer
-0.71
²¾
-0.62
Role
-0.62
Cutter
-0.62
Sung
-0.61
Contents
-0.61
Ĥ¬
-0.60
Required
-0.59
Cho
-0.58
soType
-0.58
POSITIVE LOGITS
'll
1.48
're
1.43
've
1.29
reap
1.08
'd
1.07
gain
0.95
get
0.94
aves
0.91
owe
0.91
can
0.90
Activations Density 0.104%