INDEX
Explanations
relationships and connections among individuals
New Auto-Interp
Negative Logits
granddaughter
-0.18
grandson
-0.17
INGER
-0.17
ihan
-0.15
niece
-0.15
доÑĩ
-0.15
daughter
-0.14
418
-0.14
uthor
-0.14
iliz
-0.14
POSITIVE LOGITS
partner
0.33
partner
0.27
mentor
0.26
partners
0.26
mate
0.25
Partner
0.24
Partner
0.24
companion
0.24
nem
0.24
muse
0.23
Activations Density 0.158%