INDEX

Explanations

punctuation marks and sentence endings

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

 PLEASE

-0.08

PLEASE

-0.07

 please

-0.07

WARNING

-0.07

 Writes

-0.07

Ah

-0.06

 WARNING

-0.06

 Appears

-0.06

Oops

-0.06

Ain

-0.06

POSITIVE LOGITS

We

0.10

We

0.10

we

0.10

Our

0.09

 really

0.09

Our

0.09

we

0.08

 somebody

0.08

our

0.08

 part

0.07

Activations Density 0.069%