INDEX

Explanations

characters or symbols related to mathematical parameters or representations

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

“

-0.07

 America

-0.07

 Bush

-0.07

‘

-0.06

 “âĢ¦

-0.06

 Obama

-0.06

 (“

-0.06

USA

-0.06

USA

-0.06

FOX

-0.06

POSITIVE LOGITS

 Cald

0.10

 party

0.10

 labour

0.10

party

0.09

 Labour

0.09

 Scar

0.09

Labour

0.08

 NÃ³

0.08

 Parliamentary

0.08

 Party

0.08

Activations Density 0.004%