INDEX

Explanations

be + adjective/adverb

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

ly

2.88

or

2.47

ay

2.27

nya

2.26

ry

2.20

犸

2.16

es

2.15

dain

2.12

escent

2.12

POSITIVE LOGITS

 पाण्डे

2.03

ಲೀ

1.97

gebracht

1.96

하려고

1.91

 totalement

1.91

ɖ

1.91

ʛ

1.89

িতেছিল

1.89

Sehr

1.88

Луч

1.87

Activations Density 0.487%