INDEX

Explanations

specific characters or symbols that signal non-standard or coded 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

 Retail

-0.06

 Spicer

-0.06

Retail

-0.06

ecial

-0.06

ãĥªãĤ«

-0.06

_vendor

-0.05

 retailer

-0.05

oplayer

-0.05

blk

-0.05

odia

-0.05

POSITIVE LOGITS

 Couch

0.24

 couch

0.22

 hosts

0.14

 sofa

0.13

 host

0.13

 sofas

0.12

 Sofa

0.12

 Host

0.12

 hostel

0.12

hosts

0.12

Activations Density 0.005%