INDEX

Explanations

Principal

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 warn

-0.68

 beginnetje

-0.66

principalColumn

-0.63

contentLoaded

-0.63

adpleegd

-0.63

 Principal

-0.60



-0.60

 tartalomajánló

-0.60

aarrggbb

-0.59

новништво

-0.58

POSITIVE LOGITS

Gone

0.50

She

0.50

 broadly

0.50

ραγ

0.49

 kartu

0.48

doe

0.48

gone

0.46

rippa

0.45

 polyps

0.45

ction

0.45

Activations Density 0.024%