INDEX
Explanations
pronouns 'his', 'her', 'its', and 'their' followed by a possessive noun
pronouns referring to individuals or their teams
New Auto-Interp
Negative Logits
agre
-0.68
Features
-0.66
ONEY
-0.63
ydia
-0.63
:(
-0.62
ijn
-0.60
includ
-0.59
gio
-0.59
&&
-0.58
ĨĴ
-0.58
POSITIVE LOGITS
axter
0.74
allies
0.72
pet
0.71
cohorts
0.69
friends
0.69
pals
0.68
colleagues
0.67
surrounding
0.66
surroundings
0.66
brothers
0.65
Activations Density 0.231%