INDEX

Explanations

symbols or characters associated with mathematical and scientific notation

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

‘

-0.11

‘

-0.09

’

-0.07

’

-0.07

“

-0.07

’re

-0.06

’Brien

-0.06

’s

-0.06

’ll

-0.06

”

-0.06

POSITIVE LOGITS

 Letters

0.10

 Jews

0.09

 Letter

0.09

 LETTER

0.09

 Languages

0.09

Letters

0.09

 Judaism

0.08

 Constructs

0.08

 Mono

0.08

Jew

0.08

Activations Density 0.003%