INDEX
Explanations
occurrences of images within the text
New Auto-Interp
Negative Logits
lier
-0.16
igner
-0.15
osa
-0.15
-0.15
l
-0.15
Pag
-0.14
imento
-0.14
wend
-0.14
lop
-0.14
alie
-0.14
POSITIVE LOGITS
اÙĦرÙħزÙĬØ©
0.19
result
0.18
/gif
0.18
-result
0.17
result
0.16
rescia
0.15
credit
0.15
zik
0.15
ennen
0.15
Result
0.15
Activations Density 0.015%