INDEX
Explanations
mentions of the brand "Budweiser."
pronouns related to collective identity
New Auto-Interp
Negative Logits
corro
-0.64
juggling
-0.62
coping
-0.61
spare
-0.60
steep
-0.58
PLUS
-0.56
rapists
-0.56
ceilings
-0.55
pim
-0.55
finance
-0.55
POSITIVE LOGITS
e
0.95
cker
0.87
hn
0.86
lda
0.86
gm
0.86
lla
0.85
ttes
0.85
cki
0.84
bel
0.83
llo
0.82
Activations Density 0.078%