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

 said

-1.53

not

-1.38

 varied

-1.35

-1.34

 still

-1.30

-1.23

 Still

-1.20

 Another

-1.13

 inneces

-1.11

Re

-1.10

POSITIVE LOGITS

यह

1.32

gewöhn

1.30

ТЕЛЬ

1.27

Latino

1.27

 साधारण

1.27

 congrès

1.25

 प्रोड

1.24

Exper

1.23

 खरी

1.23

ЦИЯ

1.21

Activations Density 0.075%