INDEX
Explanations
references to familial relationships and heritage
New Auto-Interp
Negative Logits
вед
-0.14
513
-0.14
oldt
-0.14
icros
-0.14
Couples
-0.14
ender
-0.13
initely
-0.13
kontakte
-0.13
Ø´ÙĪØ±
-0.13
enden
-0.13
POSITIVE LOGITS
son
1.16
sons
0.97
Son
0.87
son
0.87
daughter
0.85
Son
0.82
SON
0.79
.son
0.77
sons
0.73
Sons
0.72
Activations Density 0.669%