INDEX
Explanations
mentions of "Tel Aviv" and related terms
New Auto-Interp
Negative Logits
iston
-0.16
nech
-0.16
arov
-0.16
flags
-0.14
revert
-0.14
uner
-0.14
еÑĢп
-0.13
물ìĿĦ
-0.13
:`~
-0.13
.tech
-0.13
POSITIVE LOGITS
éfono
0.19
Aviv
0.19
439
0.17
967
0.16
905
0.15
ores
0.15
iminal
0.15
Jerome
0.15
zych
0.14
Strict
0.14
Activations Density 0.023%