INDEX
Explanations
periods at the end of sentences
New Auto-Interp
Negative Logits
imi
-0.14
weigh
-0.14
Äijây
-0.14
est
-0.14
taps
-0.13
Voor
-0.13
adu
-0.13
amu
-0.13
acs
-0.13
mlin
-0.13
POSITIVE LOGITS
ClassName
0.15
ofType
0.14
Initialized
0.14
lett
0.13
enta
0.13
isque
0.13
zen
0.13
пов
0.13
292
0.13
sen
0.13
Activations Density 0.022%