INDEX
Explanations
phrases related to the publication Gizmodo
names of individuals and entities
New Auto-Interp
Negative Logits
owship
-0.77
SPONSORED
-0.75
ufact
-0.70
SAY
-0.66
ISA
-0.66
pection
-0.65
srfAttach
-0.63
EMOTE
-0.63
acebook
-0.63
ACTIONS
-0.62
POSITIVE LOGITS
vous
1.01
ÅĤ
0.77
acan
0.76
Khalid
0.76
hur
0.74
ooth
0.74
owicz
0.71
anca
0.70
ovsky
0.68
orno
0.68
Activations Density 0.262%