INDEX

Explanations

words that express opinions or judgements about events and circumstances

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 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

toMatchSnapshot

-0.54

 honestly

-0.49

platte

-0.48

 pretty

-0.48

clientY

-0.48

<bos>

-0.47

charCodeAt

-0.46

pretty

-0.46

ogaster

-0.46

 Advis

-0.45

POSITIVE LOGITS

InitVars

0.70

 purpoſe

0.66

Datuak

0.66

 Reſ

0.63

ſelf

0.62

 Theſe

0.62

:+:

0.61

 wireType

0.60

 NIOS

0.60

 nahilalakip

0.59

Activations Density 1.137%