INDEX
Explanations
prominent political figures and leaders in news articles
names of political figures and important leaders
New Auto-Interp
Negative Logits
ãĥ¼ãĥĨ
-0.80
ãĥ´ãĤ¡
-0.72
Load
-0.70
76561
-0.69
ipl
-0.67
Els
-0.67
ãĥ¼ãĥĨãĤ£
-0.66
ãĤ¹
-0.64
ãĥł
-0.63
ãĥĢ
-0.63
POSITIVE LOGITS
attends
0.99
reacted
0.97
reacts
0.97
gestures
0.94
greets
0.93
apologized
0.93
condemned
0.92
participates
0.92
pauses
0.91
welcomed
0.90
Activations Density 0.263%