INDEX
Explanations
references to the state of Oregon
references to the state of Oregon
New Auto-Interp
Negative Logits
hare
-0.88
maid
-0.83
BOOK
-0.81
seiz
-0.77
SHIP
-0.71
stroke
-0.69
pter
-0.69
bler
-0.67
creen
-0.67
fare
-0.66
POSITIVE LOGITS
Oregon
1.06
sylvania
0.99
Ducks
0.94
ians
0.93
State
0.92
Timbers
0.91
icut
0.91
Oregon
0.90
Hills
0.88
ian
0.85
Activations Density 0.016%