INDEX
Explanations
references to political figures and their roles in government
New Auto-Interp
Negative Logits
nev
-0.15
morgan
-0.14
haven
-0.13
alli
-0.13
pective
-0.13
/topics
-0.13
Rosenstein
-0.13
ubic
-0.13
[${-0.13
ìŀĦ
-0.13
POSITIVE LOGITS
visited
0.18
pres
0.18
visited
0.17
ribbon
0.16
Visited
0.15
personally
0.15
participate
0.15
present
0.15
along
0.15
,address
0.15
Activations Density 0.073%