INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

。...

0.93

 propried

0.90

畤

0.89

 ettevõ

0.89

Შ

0.88

 semelh

0.88

 adiab

0.87

<unused1008>

0.86

 quinze

0.86

⁈

0.86

POSITIVE LOGITS

 Symptoms

1.35

 Blood

1.15

 What

1.10

1.09

How

1.08

Low

1.05

 Normal

1.04

 symptoms

0.98

 blood

0.98

 Signs

0.97

Activations Density 0.208%

No Known Activations