INDEX
Explanations
references to internet memes
references to memes and meme culture
New Auto-Interp
Negative Logits
charism
-0.68
hani
-0.66
Dull
-0.65
enting
-0.64
trave
-0.63
glim
-0.63
appointments
-0.63
Yards
-0.62
rament
-0.61
Thro
-0.61
POSITIVE LOGITS
memes
1.04
meme
1.02
pty
0.82
ery
0.80
oji
0.78
bers
0.78
stress
0.72
etically
0.72
iverse
0.71
poster
0.70
Activations Density 0.016%