INDEX
Explanations
entities related to occupations and roles in various fields, especially in entertainment and academia
New Auto-Interp
Negative Logits
ills
-0.16
ibel
-0.15
ладÑĥ
-0.15
owane
-0.14
Friendly
-0.14
alone
-0.13
advisory
-0.13
itself
-0.13
lagen
-0.13
TREE
-0.13
POSITIVE LOGITS
who
0.24
who
0.20
active
0.19
whose
0.17
ÙĪÙĦد
0.17
born
0.17
active
0.16
اÙĩÙĦ
0.16
Born
0.16
è°ģ
0.16
Activations Density 0.038%