INDEX

Explanations

html attributes className style src

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

}}$

-1.50

งิน

-1.47

بله

-1.42

ถ้า

-1.41

';

-1.40

]))

-1.37

 Jahrhundert

-1.33

 aient

-1.31

</blockquote>

-1.30

álním

-1.30

POSITIVE LOGITS

 with

2.02

nitř

2.00

 either

1.81

 this

1.52

 they

1.48

 باید

1.44

 being

1.40

しましたが

1.39

the

1.38

 shouldn

1.38

Activations Density 0.001%