INDEX
Explanations
personal relationships and connections among individuals
New Auto-Interp
Negative Logits
vez
-0.19
ách
-0.15
il
-0.15
afc
-0.14
province
-0.14
anie
-0.14
ipo
-0.14
brat
-0.13
DevComponents
-0.13
Matchers
-0.13
POSITIVE LOGITS
personally
0.17
irut
0.15
myself
0.15
personal
0.15
allee
0.15
ucker
0.14
oshi
0.14
414
0.14
orpor
0.14
hte
0.14
Activations Density 0.846%