INDEX
Explanations
instances of the possessive pronoun "his"
references to possession or ownership
New Auto-Interp
Negative Logits
ocument
-0.80
itect
-0.80
anguage
-0.77
izabeth
-0.71
Trend
-0.71
ablishment
-0.69
hari
-0.68
largeDownload
-0.68
Recomm
-0.67
DN
-0.67
POSITIVE LOGITS
own
1.60
panic
1.40
father
1.15
wife
1.13
Majesty
1.12
predecessor
1.02
sing
1.00
brother
0.99
superiors
0.98
namesake
0.97
Activations Density 0.281%