INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
lus
1.04
Lod
1.01
Lus
1.00
Lus
0.95
sla
0.93
slo
0.92
Sle
0.92
SLE
0.91
Lue
0.91
SEL
0.90
POSITIVE LOGITS
Murray
0.99
Murray
0.94
Miranda
0.91
Mir
0.85
inversion
0.84
MIR
0.84
Trump
0.81
Panch
0.80
quadru
0.80
quad
0.79
Activations Density 2.961%