INDEX
Explanations
titles and authors of romance novels or series
New Auto-Interp
Negative Logits
祥
-0.19
пÑĢоз
-0.15
ahn
-0.15
omon
-0.15
orch
-0.15
ylan
-0.15
aminer
-0.14
ationToken
-0.14
GM
-0.14
gig
-0.14
POSITIVE LOGITS
Jamie
0.31
Jamie
0.29
Fraser
0.26
Claire
0.23
Jaime
0.22
Scotland
0.22
Highland
0.21
Glasgow
0.21
Scottish
0.21
Highlander
0.21
Activations Density 0.003%