INDEX
Explanations
references to logos
references to logos and branding elements
New Auto-Interp
Negative Logits
hower
-0.80
neau
-0.74
hurst
-0.72
kus
-0.72
Ago
-0.71
theless
-0.67
auld
-0.63
ieri
-0.62
erve
-0.62
astern
-0.62
POSITIVE LOGITS
logos
1.03
logo
0.92
plates
0.86
Logo
0.84
Doodle
0.82
slogan
0.78
trademarks
0.77
recognition
0.76
synonymous
0.75
redesign
0.75
Activations Density 0.050%