INDEX

Explanations

wikipedia references

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

 this

1.01

of

1.00

 worthy

0.97

 우리의

0.93

 contributes

0.91

창

0.89

 these

0.89

 exerts

0.88

 그런

0.87

 motivates

0.86

POSITIVE LOGITS

 suivantes

1.46

 suivante

1.41

 immediatamente

1.28

 alfabeto

1.27

 suivant

1.25

 siguiente

1.23

 suivants

1.23

 टॉपर

1.23

 auxquelles

1.20

 größte

1.19

Activations Density 0.088%