INDEX
Explanations
references to full names and surnames, particularly in the context of searching for individuals
New Auto-Interp
Negative Logits
ichick
-0.15
labeling
-0.14
'icon
-0.14
Prometheus
-0.14
zan
-0.14
yg
-0.13
abee
-0.13
orthand
-0.13
KF
-0.13
ekk
-0.13
POSITIVE LOGITS
last
0.40
given
0.37
Last
0.36
-last
0.35
given
0.34
Last
0.34
Given
0.34
last
0.33
surname
0.33
_last
0.32
Activations Density 0.147%