INDEX
Explanations
proper nouns and specific names related to places and people
New Auto-Interp
Negative Logits
Mash
-0.16
Sphinx
-0.15
essian
-0.15
Zucker
-0.15
Egyptian
-0.15
Jama
-0.15
Egypt
-0.14
Patriot
-0.14
Egypt
-0.14
KY
-0.14
POSITIVE LOGITS
Tim
0.28
Tim
0.24
Portuguese
0.22
tim
0.22
tim
0.21
Indonesian
0.21
East
0.20
Jakarta
0.20
Tet
0.20
TIM
0.20
Activations Density 0.001%