INDEX

Explanations

word endings and punctuation

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

ᄅ

2.17



2.15

‖</

2.14

клада

2.13

yap

2.10



2.09

‛

2.08

ष्कार

2.08

淉

2.07



2.06

POSITIVE LOGITS

xiety

2.10

usk

1.86

你會

1.75

ee

1.72

sworth

1.70

forth

1.70

ology

1.69

ekt

1.65

oggle

1.65

umab

1.65

Activations Density 0.002%