INDEX
Explanations
terms related to native species and their attributes
New Auto-Interp
Negative Logits
mit
-0.15
wend
-0.15
/animations
-0.15
ares
-0.14
tha
-0.14
rosso
-0.14
ase
-0.14
rint
-0.14
øy
-0.14
sm
-0.13
POSITIVE LOGITS
/native
0.21
/local
0.18
ials
0.17
-born
0.17
ovice
0.15
ãģ¾ãĤĬ
0.15
aleza
0.15
ously
0.14
itably
0.14
Düz
0.14
Activations Density 0.020%