INDEX
Explanations
connections and discussions about familial relationships
New Auto-Interp
Negative Logits
ksen
-0.17
inv
-0.15
achs
-0.14
ntag
-0.14
heimer
-0.14
Loft
-0.14
bindung
-0.14
inks
-0.14
ÃŁe
-0.14
stro
-0.14
POSITIVE LOGITS
ge
0.25
gee
0.24
gem
0.20
gest
0.20
ging
0.20
z
0.19
geb
0.17
anging
0.17
gear
0.17
zu
0.17
Activations Density 0.026%