INDEX
Explanations
specific forms or variations of food-related words
New Auto-Interp
Negative Logits
ÎŃÏģει
-0.15
setC
-0.15
uations
-0.14
ýn
-0.13
ÑĢай
-0.13
zeros
-0.13
UInteger
-0.12
axter
-0.12
uat
-0.12
ActiveSupport
-0.12
POSITIVE LOGITS
i
0.84
I
0.49
и
0.45
ÛĮ
0.39
iв
0.38
i
0.38
iT
0.38
×Ļ
0.38
iParam
0.37
ÙĬ
0.37
Activations Density 0.215%