INDEX

Explanations

code blocks and their results

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

any

-1.98

romas

-1.66

 when

-1.56

gencias

-1.51

 Polícia

-1.46

 just

-1.44

áver

-1.36

 schaff

-1.35

Solución

-1.32

-1.31

POSITIVE LOGITS

 were

1.53

待って

1.41

OGLE

1.34

it

1.33

valget

1.32

čeno

1.32

How

1.30

 spokoj

1.30

にとっては

1.28

 クルー

1.28

Activations Density 0.004%