INDEX

Explanations

District, ku, Area, 识, 交流

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

that

-2.44

 offizielle

-2.38

 که

-2.38

 letzte

-2.30

する

-2.28

ݯ

-2.27

 größte

-2.27



-2.25

してました

-2.25

吀

-2.22

POSITIVE LOGITS

3.80

\_

2.66

2.64

 leur

2.55

—

2.31

</em>

2.27

}{

2.25

\\

2.23

am

2.23

</h4>

2.17

Activations Density 0.002%