INDEX
Explanations
mentions of the word "squad" in various contexts
New Auto-Interp
Negative Logits
utenberg
-0.75
pport
-0.71
orgetown
-0.71
naissance
-0.71
pire
-0.70
Downloadha
-0.69
éĽ
-0.69
ocaust
-0.67
gra
-0.66
isin
-0.65
POSITIVE LOGITS
rons
1.68
mates
1.04
mates
1.00
members
0.91
alid
0.84
leader
0.80
members
0.80
mate
0.75
rosters
0.75
aris
0.75
Activations Density 0.020%