INDEX
Explanations
references to or descriptions of GIFs
mentions of GIFs
New Auto-Interp
Negative Logits
arios
-0.74
ophy
-0.68
idem
-0.66
omaly
-0.65
Austral
-0.64
heid
-0.64
oney
-0.64
andra
-0.64
ologically
-0.62
role
-0.62
POSITIVE LOGITS
GIF
1.15
gif
1.03
TED
0.99
Thumbnails
0.86
FIX
0.82
eries
0.81
SIGN
0.78
TION
0.76
FB
0.74
TEXT
0.73
Activations Density 0.006%