INDEX
Explanations
mentions of organizations, brands, or teams
New Auto-Interp
Head Attr Weights
0:0.32
1:0.04
2:0.03
3:0.05
4:0.13
5:0.09
6:0.06
7:0.03
8:0.08
9:0.06
10:0.03
11:0.03
Negative Logits
handshake
-1.93
unrecogn
-1.68
executed
-1.68
prost
-1.66
Superior
-1.64
equivalent
-1.61
mechanically
-1.58
coron
-1.58
forged
-1.58
prototyp
-1.55
POSITIVE LOGITS
�
2.25
aily
2.25
iquette
2.24
atalie
2.12
politics
2.07
actionGroup
2.06
ispers
2.03
news
2.02
podcast
2.02
omics
2.02
Activations Density 0.012%