INDEX
Explanations
references to specific individuals and their roles within an institutional or organizational context
New Auto-Interp
Negative Logits
igi
-0.16
SCRI
-0.15
mites
-0.14
eon
-0.14
ecimal
-0.14
imity
-0.14
swagen
-0.14
uguay
-0.14
elper
-0.14
rove
-0.14
POSITIVE LOGITS
Seg
0.26
Bol
0.24
Rot
0.24
Fun
0.22
Prec
0.21
Fest
0.21
Fol
0.20
Seg
0.20
seg
0.20
Tem
0.19
Activations Density 0.045%