INDEX

Explanations

features or contains

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 auttaa

-0.96

 menilai

-0.96

ataa

-0.92

 enää

-0.90

 menikah

-0.90

骡

-0.89

 vœux

-0.88

Punkt

-0.88

tizia

-0.88

 пишет

-0.87

POSITIVE LOGITS

 featuring

1.16

 feature

1.13

 contain

1.13

Featuring

1.12

 offer

1.10

 Featuring

1.09

 features

1.09

 Features

1.08

 contains

1.06

包含

1.03

Activations Density 0.052%