INDEX
Explanations
linguistic terms and etymologies
New Auto-Interp
Negative Logits
odom
-0.15
Mein
-0.15
ils
-0.15
Dot
-0.14
dot
-0.14
ilar
-0.14
aces
-0.14
ÑģÑıÑĤ
-0.14
comma
-0.14
irim
-0.14
POSITIVE LOGITS
root
0.26
roots
0.23
root
0.21
Latin
0.21
-root
0.20
_root
0.19
Middle
0.19
Proto
0.19
derivatives
0.19
.root
0.19
Activations Density 0.042%