INDEX
Explanations
references to events or gatherings that have a significant number of attendees or participants
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.08
3:0.05
4:0.02
5:0.06
6:0.07
7:0.10
8:0.07
9:0.12
10:0.07
11:0.26
Negative Logits
rapport
-1.20
stabilized
-1.18
adaptive
-1.15
attribution
-1.14
Stability
-1.13
Behavior
-1.11
Identified
-1.10
arget
-1.07
Retrieved
-1.04
affinity
-1.03
POSITIVE LOGITS
packed
1.26
crammed
1.25
overflowing
1.18
packed
1.17
sweaty
1.16
illion
1.15
fest
1.14
piled
1.12
unch
1.10
overwhel
1.09
Activations Density 0.013%