INDEX
Explanations
mentions of the name "Aleppo"
references to the name "Ale."
New Auto-Interp
Negative Logits
enegger
-0.66
ancial
-0.65
JUSTICE
-0.62
FTA
-0.61
Everyday
-0.58
IMAGES
-0.58
align
-0.57
NX
-0.57
karma
-0.57
prominently
-0.56
POSITIVE LOGITS
jandro
1.47
ppo
1.23
cia
0.97
thia
0.97
ivia
0.95
vez
0.93
oric
0.91
tta
0.91
tha
0.89
mb
0.88
Activations Density 0.022%