INDEX
Explanations
references to tear-inducing situations or objects
expressions related to crying or emotional distress
New Auto-Interp
Negative Logits
ancial
-0.74
eton
-0.72
POL
-0.71
enhagen
-0.69
abilities
-0.65
keley
-0.65
pmwiki
-0.64
SPONSORED
-0.63
disadvant
-0.63
traveler
-0.62
POSITIVE LOGITS
bows
1.14
bow
1.02
adoes
0.96
ful
0.96
stained
0.95
fully
0.83
gas
0.82
away
0.81
stained
0.78
tears
0.78
Activations Density 0.035%