INDEX

Explanations

mathematical symbols and variables related to specific models or equations

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

‘

-0.08

 humour

-0.07

-0.06

aju

-0.06

 centres

-0.06

 whilst

-0.06

 travelling

-0.06

 anyways

-0.06

['

-0.06

 neighbouring

-0.06

POSITIVE LOGITS

 testers

0.13

 tester

0.11

 Editors

0.09

Tester

0.09

 Tester

0.09

Editors

0.09

 winner

0.09

tester

0.08

our

0.08

 editors

0.08

Activations Density 0.007%