INDEX
Explanations
sentences that describe ownership or involvement in various activities or organizations
New Auto-Interp
Negative Logits
olle
-0.17
Į
-0.15
prere
-0.15
GPS
-0.14
Tri
-0.14
attended
-0.14
Latter
-0.14
Gan
-0.14
utm
-0.14
tri
-0.14
POSITIVE LOGITS
abus
0.23
arb
0.19
uali
0.17
avr
0.16
isz
0.16
aho
0.15
ahren
0.15
lero
0.14
itself
0.14
ibold
0.14
Activations Density 0.131%