INDEX

Explanations

HTML structure and placeholder images

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ណ

1.96

 notary

1.95

 हनु

1.93

σό

1.92

 sauna

1.92

ដំណើរ

1.89

옻

1.88

 jacuzzi

1.87

 đau

1.86

栆

1.85

POSITIVE LOGITS

of

1.47

↵↵

1.37

1.30

<start_of_image>

1.30

Of

1.28

 Democr

1.20

 their

1.16

Column

1.14

 Column

1.13

↵↵↵↵

1.12

Activations Density 0.000%

No Known Activations