INDEX
Explanations
pronouns and verbs indicating possession or relationship
pronouns, especially second-person pronouns
New Auto-Interp
Negative Logits
unspecified
-0.68
math
-0.65
vine
-0.63
³³³³
-0.60
None
-0.59
unofficial
-0.58
Gerard
-0.58
Evolution
-0.57
Dres
-0.57
Unlimited
-0.57
POSITIVE LOGITS
've
1.00
chose
0.90
'd
0.89
arers
0.85
envisioned
0.82
're
0.81
aves
0.81
wrote
0.80
inherited
0.80
adore
0.78
Activations Density 0.127%