INDEX
Explanations
references to digital communication and community involvement
New Auto-Interp
Negative Logits
[
-0.16
oulos
-0.15
.SDK
-0.15
âĢª
-0.14
olib
-0.14
Ferd
-0.14
http
-0.14
ereo
-0.13
elerik
-0.13
[.
-0.13
POSITIVE LOGITS
—↵
0.24
—↵↵
0.22
–
0.20
—
0.20
Uh
0.19
Yeah
0.19
um
0.18
COVID
0.18
Um
0.18
uh
0.18
Activations Density 0.009%