INDEX
Explanations
references to specific brands or entities
New Auto-Interp
Negative Logits
venes
-0.15
uted
-0.15
presso
-0.15
ANEL
-0.14
anel
-0.14
pees
-0.14
yas
-0.14
letes
-0.14
MetroFramework
-0.14
rovers
-0.14
POSITIVE LOGITS
Sp
0.26
sp
0.22
.Sp
0.20
Sp
0.19
emann
0.19
(SP
0.19
-sp
0.19
otted
0.19
.sp
0.18
illo
0.17
Activations Density 0.020%