INDEX
Explanations
mentions of the location "Washington, D.C."
references to a specific geographic location, particularly Washington D.C
New Auto-Interp
Negative Logits
Maker
-0.80
éĹĺ
-0.72
edIn
-0.67
Izan
-0.66
nings
-0.64
Finnish
-0.64
schild
-0.64
Reviewer
-0.63
Sanskrit
-0.62
cies
-0.62
POSITIVE LOGITS
.,
1.29
.?
1.09
.;
0.95
.,"
0.94
./
0.93
.:
0.89
.—
0.89
.-
0.82
adel
0.81
upid
0.81
Activations Density 0.025%