INDEX

Explanations

digits

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

“

-0.53

-0.50

…

-0.43

-0.40

…

-0.38

...

-0.36

and

-0.36

red

-0.36

<eos>

-0.35

POSITIVE LOGITS

 kasarigan

1.34

ItemBackground

1.21

 myſelf

1.18

 Theſe

1.13

 itſelf

1.13

 Jefus

1.10

Efq

1.09

 Monfieur

1.03

ſelf

1.00

 Majefty

1.00

Activations Density 0.383%