INDEX

Explanations

elements related to programming and software structure

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

 tales

-0.08

Maps

-0.08

Forms

-0.07

 Stories

-0.07

 Lists

-0.06

ngen

-0.06

 Maps

-0.06

 Forms

-0.06

 Websites

-0.06

PTS

-0.06

POSITIVE LOGITS

 fields

0.18

 methods

0.17

methods

0.15

 Fields

0.13

fields

0.13

_methods

0.13

 Methods

0.13

_fields

0.13

Fields

0.12

.fields

0.12

Activations Density 0.002%