INDEX

Explanations

names followed by actions or descriptions

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

 those

-1.27

rasa

-1.20

᱘

-1.09

 организаций

-1.09

Algae

-1.09

minate

-1.08

Faktor

-1.08

junge

-1.07

čina

-1.07

 ermöglichen

-1.07

POSITIVE LOGITS

 articol

1.26

mientras

1.21

 GetAll

1.20

na

1.17

 hiver

1.14

 Oficina

1.11

 ramo

1.09

배

1.08

 parlé

1.07

 getB

1.07

Activations Density 0.297%