INDEX

Explanations

names of people and places

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

-1.62

be

-1.41

ﬄ

-1.40

 also

-1.35

 each

-1.31

但

-1.27

っぽい

-1.19

 that

-1.18

of

-1.17

 भार

-1.14

POSITIVE LOGITS

 vänner

1.48

Polizei

1.45

 coelho

1.42

跸

1.41

ﮧ

1.38

 kalem

1.38

 måneder

1.37

KNOWN

1.36

 متحد

1.36

Kedua

1.34

Activations Density 0.067%