INDEX
Explanations
proper nouns
instances of the possessive pronoun "His."
New Auto-Interp
Negative Logits
shopping
-0.70
ribbon
-0.68
optional
-0.62
offline
-0.60
square
-0.59
online
-0.58
updated
-0.56
we
-0.55
,
-0.55
survey
-0.55
POSITIVE LOGITS
His
3.12
his
2.22
His
2.10
He
1.99
HIS
1.66
Himself
1.52
Their
1.42
him
1.37
his
1.36
He
1.29
Activations Density 0.008%