INDEX
Explanations
variations of the word "enslave" and terms related to ownership or property
New Auto-Interp
Negative Logits
ÃŃs
-0.16
à¯ģ
-0.15
issan
-0.15
ίνα
-0.14
ött
-0.14
oste
-0.14
indi
-0.14
\Abstract
-0.14
ined
-0.14
å¡ļ
-0.14
POSITIVE LOGITS
á
0.36
ay
0.34
ai
0.34
Äģ
0.34
af
0.34
aj
0.32
az
0.32
ao
0.32
ae
0.32
ap
0.31
Activations Density 0.330%