INDEX
Explanations
terms indicating size or scale
New Auto-Interp
Negative Logits
lessly
-0.17
rary
-0.16
resp
-0.15
dit
-0.14
ving
-0.14
±
-0.14
ray
-0.14
صÙĩ
-0.14
450
-0.14
resp
-0.14
POSITIVE LOGITS
-scale
0.41
scale
0.23
-sized
0.21
/small
0.21
Scale
0.20
scale
0.20
Scale
0.19
gest
0.19
hetto
0.19
/big
0.19
Activations Density 0.146%