INDEX

Explanations

word

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

 word

-1.12

 Word

-0.77

word

-0.77

ContentAsync

-0.77

Word

-0.73

 phrase

-0.72

 WORD

-0.71

WORD

-0.66

 term

-0.65

FormTagHelper

-0.60

POSITIVE LOGITS

GMENT

0.54

0.50

ary

0.50

 SECT

0.49

 resourceCulture

0.49

yship

0.49

0.48

 BorderSide

0.47

RUnlock

0.47

 hinzu

0.47

Activations Density 0.056%