INDEX
Explanations
the word "big" in various contexts
New Auto-Interp
Negative Logits
itage
-0.15
isque
-0.15
prus
-0.15
inator
-0.15
aras
-0.14
ors
-0.14
oden
-0.14
天åłĤ
-0.14
agine
-0.14
AnimationFrame
-0.14
POSITIVE LOGITS
oted
0.26
-scale
0.22
elow
0.22
/big
0.20
/small
0.19
gest
0.19
-ticket
0.18
gie
0.18
enough
0.18
ears
0.18
Activations Density 0.043%