INDEX
Explanations
references to "native" entities, particularly plants and populations
New Auto-Interp
Negative Logits
wend
-0.18
mit
-0.16
abin
-0.16
tha
-0.15
ares
-0.15
FactoryBot
-0.14
rosso
-0.14
agger
-0.14
manship
-0.14
iw
-0.14
POSITIVE LOGITS
/native
0.23
ials
0.18
-born
0.17
/local
0.17
unset
0.15
ities
0.15
ialis
0.15
orney
0.15
itarian
0.15
Düz
0.14
Activations Density 0.024%