INDEX
Explanations
references to Egypt and related entities
New Auto-Interp
Negative Logits
hips
-0.86
lasses
-0.80
Kessler
-0.75
ificantly
-0.73
rils
-0.73
anza
-0.72
creen
-0.72
amins
-0.71
ivity
-0.71
lass
-0.70
POSITIVE LOGITS
hier
0.83
Egyptians
0.81
osph
0.80
Pharaoh
0.77
Air
0.77
Egyptian
0.73
Arabia
0.73
Egypt
0.71
wings
0.68
Sinai
0.67
Activations Density 0.009%