INDEX

Explanations

references to the context or state of the current object or application instance

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Bod

-0.07

ook

-0.06

å§ĵ

-0.06

enda

-0.06

 Bene

-0.06

err

-0.05

adem

-0.05

 Buster

-0.05

itter

-0.05

 Dawson

-0.05

POSITIVE LOGITS

->

0.21

->

0.14

->_

0.14

->↵

0.12

->$

0.12

âĨĴ

0.11

->{

0.10

->[

0.10

->{'

0.10

->__

0.10

Activations Density 0.008%