INDEX
Explanations
instances of the word "large" and its variations
New Auto-Interp
Negative Logits
ouro
-0.15
нимаÑĤÑĮ
-0.15
ral
-0.15
rice
-0.15
zon
-0.15
slightest
-0.15
rac
-0.14
ses
-0.14
ries
-0.14
yonel
-0.14
POSITIVE LOGITS
-scale
0.32
(er
0.19
/big
0.17
/small
0.16
onio
0.15
arg
0.15
ÏĦεÏģ
0.15
-sized
0.15
enough
0.15
Enough
0.15
Activations Density 0.047%