INDEX
Explanations
words with the special character 'ö' or related variations
New Auto-Interp
Negative Logits
anges
-0.15
ÃŃ
-0.15
iceps
-0.14
èĩ¨
-0.14
ré
-0.14
unk
-0.14
oki
-0.14
eness
-0.14
utc
-0.14
background
-0.14
POSITIVE LOGITS
cher
0.18
ön
0.16
اÙĨÙĩ
0.15
chen
0.15
ött
0.15
sten
0.14
zzo
0.14
Prim
0.14
lichen
0.14
elian
0.14
Activations Density 0.020%