INDEX

Explanations

code structure and attributes

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

to

-1.24

-1.23

--

-0.98

 these

-0.98

 offiziell

-0.97

postdata

-0.95

ceous

-0.94

่วน

-0.90

:{

-0.89

POSITIVE LOGITS

*}[

1.39

 Matériau

1.22

 nécess

1.20

lag

1.16

 alliés

1.13

 Geschlecht

1.13

ımız

1.12

тім

1.11

یری

1.10

 Jésus

1.10

Activations Density 0.067%