INDEX
Explanations
the word "desire" with various contexts and intensities
expressions of various desires and motivations
New Auto-Interp
Negative Logits
Dispatch
-0.58
umbn
-0.57
ateur
-0.56
ophon
-0.56
umenthal
-0.56
icas
-0.55
TPPStreamerBot
-0.54
mans
-0.54
chin
-0.54
Seym
-0.54
POSITIVE LOGITS
to
0.99
toward
0.98
towards
0.92
for
0.82
urable
0.79
aroused
0.77
reprene
0.76
iness
0.69
TO
0.68
cooker
0.68
Activations Density 0.117%