INDEX

Explanations

non- prefix

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

 unable

0.91

不受

0.89

 não

0.87

 любом

0.86

 Received

0.86

any

0.85

no

0.85

 Uncertainty

0.84

Any

0.84

 audacity

0.83

POSITIVE LOGITS

existent

1.46

etheless

1.43

refundable

1.30

alcoholic

1.30

 negotiable

1.27

violent

1.24

threatening

1.24

 existent

1.18

invasive

1.18

verbal

1.15

Activations Density 0.050%