INDEX

Explanations

non-standard characters and special symbols used in text

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ðŁ

-0.06

 ðŁ

-0.06

ayah

-0.06

ðĿ

-0.06

 ðŁĳ

-0.06

=<?=

-0.06

ðŁĴ

-0.05

tech

-0.05

 COVID

-0.05

POSITIVE LOGITS

 fucking

0.13

 fucked

0.12

 fuck

0.12

 fucks

0.12

 Fucking

0.12

 Fuck

0.11

 shit

0.11

 FUCK

0.11

fuck

0.11

 generosity

0.10

Activations Density 0.003%