INDEX

Explanations

morgan and associated names

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

 maravill

-3.13

</u>

-3.11

 asesin

-3.03

埽

-2.95

-2.83

 hermosos

-2.78



-2.72

 différents

-2.72

НЫХ

-2.59

気付

-2.53

POSITIVE LOGITS

3.33

𖥧

2.72

na

2.69

</td>

2.61

</h2>

2.58

In

2.48

ቍ

2.44

 Each

2.38

To

2.34

Activations Density 0.005%