INDEX
Explanations
numerical values and quantities
New Auto-Interp
Negative Logits
ingham
-0.19
argin
-0.15
آبÛĮ
-0.15
rı
-0.15
ofday
-0.14
íĬ
-0.14
olean
-0.14
Floors
-0.14
ignment
-0.14
à¯į
-0.14
POSITIVE LOGITS
oise
0.14
embros
0.14
kker
0.14
omat
0.14
ANGLE
0.14
pter
0.13
à¹Ģà¸Ī
0.13
Bair
0.13
apo
0.13
ÚĨÙĩ
0.13
Activations Density 0.093%