INDEX
Explanations
mentions of the city Tel Aviv
references to Tel Aviv
New Auto-Interp
Negative Logits
ptic
-0.66
clot
-0.66
Pyth
-0.66
perature
-0.65
inges
-0.63
INAL
-0.63
enegger
-0.61
Logged
-0.60
asking
-0.60
graded
-0.59
POSITIVE LOGITS
Aviv
1.53
Juda
1.03
Torah
0.90
Netanyahu
0.88
anyahu
0.86
×
0.82
aretz
0.79
Jerusalem
0.78
arna
0.78
heim
0.77
Activations Density 0.006%