INDEX
Explanations
instances of the word "okay" or variations of it
New Auto-Interp
Negative Logits
/Foundation
-0.15
utin
-0.15
CEF
-0.15
rail
-0.14
umer
-0.14
zin
-0.14
Uploaded
-0.14
ĭ
-0.14
usan
-0.14
zos
-0.14
POSITIVE LOGITS
oser
0.16
channels
0.16
hoff
0.15
lettes
0.14
ense
0.14
echn
0.13
eva
0.13
ãĥ«ãĤ¯
0.13
pesso
0.13
reserved
0.13
Activations Density 0.027%