INDEX
Explanations
verbs that express creation or production
New Auto-Interp
Negative Logits
tec
-0.15
Advantage
-0.14
acin
-0.14
uzzi
-0.14
^{°}-0.14
apolis
-0.13
inya
-0.13
rome
-0.13
sein
-0.13
ield
-0.13
POSITIVE LOGITS
sure
0.17
arpa
0.16
strides
0.15
¼
0.15
908
0.15
waves
0.14
æĪ¦
0.14
leine
0.14
ÑĢап
0.14
Waves
0.14
Activations Density 0.110%