INDEX
Explanations
mentions of the name "Kristin" and its variations in the text
New Auto-Interp
Negative Logits
gon
-0.15
Muham
-0.15
owl
-0.15
hatt
-0.15
eldon
-0.14
548
-0.14
traits
-0.14
ikit
-0.14
Rubin
-0.14
559
-0.13
POSITIVE LOGITS
opher
0.26
offer
0.17
OF
0.16
ensen
0.16
Commons
0.16
Giang
0.15
ampo
0.15
andard
0.14
offers
0.14
allen
0.14
Activations Density 0.006%