INDEX
Explanations
references to George Orwell and his works
New Auto-Interp
Negative Logits
á»ijc
-0.16
agna
-0.14
Veranst
-0.14
_nat
-0.14
-Ta
-0.14
insk
-0.14
ereal
-0.13
iliated
-0.13
(:,
-0.13
γÏĮ
-0.13
POSITIVE LOGITS
Appointment
0.16
iyah
0.16
ÑĢоÑİ
0.16
ovah
0.15
phen
0.15
ÏĦε
0.14
initial
0.14
atos
0.14
appointment
0.14
lab
0.14
Activations Density 0.006%