INDEX
Explanations
references to Iran and related geopolitical topics
New Auto-Interp
Negative Logits
oit
-0.17
ायत
-0.16
gy
-0.15
ering
-0.15
dings
-0.15
geh
-0.15
بÙĪØ§Ø¨Ø©
-0.14
les
-0.14
ISBN
-0.14
ei
-0.14
POSITIVE LOGITS
ian
0.26
(IR
0.22
Revolutionary
0.21
ophobia
0.21
ians
0.21
anian
0.20
ious
0.20
iales
0.18
Tehran
0.18
ically
0.17
Activations Density 0.012%