INDEX

Explanations

engineering and structures

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IDL

-0.27

plevel

-0.26

ROSS

-0.25

åĹ£

-0.25

è¹©

-0.25

 accessory

-0.25

 ample

-0.24

æĴµ

-0.24

pressor

-0.24

Exposed

-0.24

POSITIVE LOGITS

 engineering

0.41

 structures

0.40

å·¥ç¨ĭ

0.39

ç»ĵæŀĦ

0.39

 Engineering

0.37

structures

0.36

 structure

0.35

 engineer

0.34

 structural

0.34

 struct

0.33

Activations Density 0.884%