INDEX
Explanations
events related to violence and destruction
New Auto-Interp
Negative Logits
Ïħγ
-0.15
iven
-0.15
ÙĪØ§Ø±
-0.15
.opend
-0.14
.appspot
-0.14
oids
-0.13
faucet
-0.13
carve
-0.13
inkel
-0.13
componentDid
-0.13
POSITIVE LOGITS
alive
0.27
eff
0.25
Alive
0.23
Alive
0.23
tires
0.22
доÑĤ
0.21
alive
0.21
unread
0.18
tyres
0.18
property
0.18
Activations Density 0.037%