INDEX

Explanations

symbols or characters used in mathematical representations or non-English text

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

ancouver

-0.08

 Stanford

-0.08

 Greenwich

-0.08

NYC

-0.08

 Wellington

-0.07

Toronto

-0.07

 Rutgers

-0.07

 Vancouver

-0.07

Oracle

-0.07

 Oracle

-0.07

POSITIVE LOGITS

 Arkansas

0.25

Ark

0.21

Ark

0.20

ark

0.16

ARK

0.15

 Fayette

0.14

ark

0.14

 Fried

0.13

 fried

0.13

AR

0.12

Activations Density 0.006%