INDEX
Explanations
specific expressions related to gift-giving and social status
New Auto-Interp
Negative Logits
rosso
-0.17
Shepard
-0.15
/Foundation
-0.15
enco
-0.15
gere
-0.14
apur
-0.14
aign
-0.14
ornings
-0.14
ssf
-0.14
ç§ij
-0.13
POSITIVE LOGITS
NET
0.17
NET
0.16
ellipt
0.15
commentators
0.15
elman
0.14
jong
0.14
peat
0.14
ãĥį
0.14
Poster
0.14
ÑĢаÑĤи
0.13
Activations Density 0.047%