INDEX
Explanations
references to wasting time or resources
New Auto-Interp
Negative Logits
adden
-0.18
resden
-0.16
owan
-0.16
Rencontres
-0.16
palms
-0.15
orex
-0.14
dens
-0.14
nten
-0.13
ollider
-0.13
δά
-0.13
POSITIVE LOGITS
waste
0.21
time
0.19
wasting
0.19
wastes
0.17
wasted
0.17
fully
0.17
Waste
0.17
kul
0.16
money
0.16
Eff
0.15
Activations Density 0.020%