INDEX
Explanations
references to ownership and owners in various contexts
New Auto-Interp
Negative Logits
us
-0.18
ute
-0.16
usc
-0.16
dozen
-0.16
ons
-0.15
vin
-0.14
ary
-0.14
anton
-0.14
ux
-0.14
zik
-0.14
POSITIVE LOGITS
/operator
0.27
-operator
0.23
/operators
0.22
/man
0.20
ship
0.20
hips
0.19
chaft
0.17
Ship
0.17
hip
0.17
SHIP
0.17
Activations Density 0.037%