INDEX
Explanations
mentions of the name "Karp"
mentions of specific names or entities
New Auto-Interp
Negative Logits
vier
-0.70
Interstitial
-0.69
differe
-0.67
mates
-0.63
creen
-0.63
maid
-0.63
Inquisition
-0.62
bane
-0.61
dilig
-0.61
unequ
-0.60
POSITIVE LOGITS
odcast
1.22
olitan
1.18
olitics
1.14
onent
1.13
edia
1.05
ools
1.04
ression
1.00
ossible
1.00
olicy
1.00
etition
0.99
Activations Density 0.051%