INDEX

Explanations

version and date information

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

 señales

-1.48

 propuestas

-1.44

ेमाल

-1.42

mistak

-1.41

 saludables

-1.34

 dobře

-1.34

 damska

-1.27

 patří

-1.25

 málo

-1.24

 labai

-1.23

POSITIVE LOGITS

to

1.73

 since

1.52

 will

1.45

 during

1.37

by

1.34

if

1.32

修为

1.30

。

1.30

 only

1.27

."

1.27

Activations Density 0.049%