INDEX
Explanations
references to prophecy and prophetic figures
New Auto-Interp
Negative Logits
rious
-0.19
arius
-0.18
aire
-0.16
itta
-0.15
iones
-0.15
ада
-0.15
veal
-0.15
ious
-0.15
ni
-0.14
Blair
-0.14
POSITIVE LOGITS
etic
0.43
ets
0.41
ét
0.37
ético
0.34
еÑĤ
0.33
etics
0.33
étique
0.32
etically
0.32
(et
0.32
etsk
0.32
Activations Density 0.069%