INDEX
Explanations
names of family members and their relationships
New Auto-Interp
Negative Logits
ids
-0.18
ednou
-0.17
rove
-0.17
ampa
-0.15
iny
-0.15
perf
-0.15
ovo
-0.15
yal
-0.14
eger
-0.14
ame
-0.14
POSITIVE LOGITS
china
0.15
coch
0.14
Getty
0.14
WPARAM
0.14
slit
0.14
ière
0.14
patch
0.13
complete
0.13
éªĮ
0.13
porr
0.13
Activations Density 0.007%