INDEX
Explanations
pronouns and nouns referring to people or groups of people
references to individuals or groups in society
New Auto-Interp
Negative Logits
<[
-0.68
apologise
-0.66
amina
-0.63
iker
-0.62
actionDate
-0.61
clerosis
-0.60
redo
-0.60
certs
-0.60
unctions
-0.59
soDeliveryDate
-0.59
POSITIVE LOGITS
»Ĵ
0.96
ãĥ¼ãĥĨ
0.76
Ĥİ
0.73
possessed
0.72
Ĥª
0.68
bestowed
0.67
magician
0.63
©¶æ
0.63
ãĥij
0.62
tains
0.62
Activations Density 0.304%