INDEX
Explanations
statistical comparisons and quantitative data in various contexts
New Auto-Interp
Negative Logits
ASI
-0.15
rani
-0.15
ıma
-0.15
ittel
-0.14
iyel
-0.14
andas
-0.13
ibase
-0.13
utto
-0.13
онÑĮ
-0.13
enum
-0.13
POSITIVE LOGITS
both
0.34
both
0.28
Both
0.25
BOTH
0.25
Both
0.24
обо
0.23
beide
0.21
_both
0.21
neither
0.20
ambos
0.19
Activations Density 0.179%