INDEX
Explanations
questions related to legal or political matters
New Auto-Interp
Negative Logits
background
-0.69
marsh
-0.68
ality
-0.65
aper
-0.64
evening
-0.63
dex
-0.63
colon
-0.63
arm
-0.62
foreground
-0.62
swamp
-0.62
POSITIVE LOGITS
Nope
1.39
Probably
1.30
Answer
1.30
Surely
1.30
Well
1.29
Certainly
1.24
Answer
1.20
Wouldn
1.19
Possibly
1.18
Why
1.18
Activations Density 0.906%