INDEX

Explanations

numbers or names followed by details

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

 that

-1.51

 after

-1.30

 both

-1.27

it

-1.24

 will

-1.23

 because

-1.23

 while

-1.22

an

-1.19

西方

-1.17

 when

-1.14

POSITIVE LOGITS

nœ

1.27

 humeur

1.25

 amitié

1.23

OTROS

1.19

ſi

1.17

 médicament

1.16

previously

1.15

Eſ

1.14

 すぎる

1.13

Цитата

1.13

Activations Density 0.009%