INDEX
Explanations
references to geographic origins or movements of people
New Auto-Interp
Negative Logits
olla
-0.16
anke
-0.15
elman
-0.15
.Foundation
-0.14
oi
-0.14
enk
-0.14
oid
-0.14
ierung
-0.14
overall
-0.14
Dum
-0.13
POSITIVE LOGITS
recurs
0.15
/to
0.14
asio
0.14
Sunshine
0.14
quential
0.13
prev
0.13
alphabet
0.13
igo
0.13
-Origin
0.13
795
0.13
Activations Density 0.085%