INDEX

Explanations

innocence and defense

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ຈັດ

0.43

 সংক্রম

0.42

CSS

0.41

 ACCESS

0.40

式

0.40

 Attention

0.40

 কল্প

0.39

lux

0.39

 ইউনিভার

0.39

 সংকোচন

0.39

POSITIVE LOGITS

 innocence

1.93

 innocent

1.81

 exoner

1.80

 innoc

1.45

 Innocent

1.45

 Innoc

1.41

 acquittal

1.27

 inoc

1.16

 acquitted

1.16

 defending

1.12

Activations Density 0.012%