INDEX
Explanations
elements related to nostalgia and memories of the past
New Auto-Interp
Negative Logits
iland
-0.16
alu
-0.16
Leban
-0.15
House
-0.15
ForObject
-0.14
yme
-0.14
Advertisement
-0.14
YST
-0.14
bubble
-0.14
@show
-0.14
POSITIVE LOGITS
hadn
0.34
had
0.28
habÃŃa
0.27
had
0.24
hadde
0.21
hade
0.20
avait
0.19
είÏĩε
0.19
Had
0.19
earlier
0.18
Activations Density 0.182%