INDEX
Explanations
references to projects or initiatives
New Auto-Interp
Head Attr Weights
0:0.03
1:0.01
2:0.05
3:0.07
4:0.04
5:0.17
6:0.01
7:0.02
8:0.04
9:0.18
10:0.23
11:0.10
Negative Logits
ghazi
-1.38
impeachment
-1.21
worse
-1.20
ocide
-1.19
decency
-1.13
fright
-1.11
starvation
-1.11
fou
-1.11
wrong
-1.10
inflic
-1.09
POSITIVE LOGITS
brainstorm
1.33
Founder
1.29
founders
1.28
prototypes
1.27
Kickstarter
1.26
partnering
1.24
ONSORED
1.23
groundbreaking
1.23
prototype
1.22
projects
1.21
Activations Density 1.716%