INDEX

Explanations

recent reports and actions

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

</strong>

-3.36

of

-3.14

餮

-2.69

蠖

-2.52

 vielen

-2.28

戗

-2.25

</sub>

-2.19

россий

-2.17

-2.14

)」

-2.13

POSITIVE LOGITS

話は

3.09

鹮

2.81

there

2.63

When

2.61

Using

2.58

Does

2.44

What

2.42

算是

2.38

这么

2.36

 μας

2.34

Activations Density 0.016%