INDEX

Explanations

proper names and abbreviations

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

Our

-3.39

</h4>

-2.95

We

-2.63

-2.56

*/

-2.55

戬

-2.50

蟥

-2.47

 avec

-2.41

\"

-2.41

"")

-2.34

POSITIVE LOGITS

 получил

2.59

嬗

2.53

 могут

2.47

 получает

2.45

 britann

2.45

家が

2.36

行

2.28

 είχε

2.27

<th>

2.23

 naïve

2.23

Activations Density 0.020%