INDEX

Explanations

words and phrases that have to do with comparisons

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

very

-0.56

 very

-0.56

Very

-0.55

 Very

-0.53

muy

-0.50

 muito

-0.47

-0.46

-0.45

 kjem

-0.44

 molto

-0.44

POSITIVE LOGITS

SharedDtor

0.92

^(@)

0.84

 للمعارف

0.80

 ་་

0.75

styleType

0.75

 doInBackground

0.75

RectangleBorder

0.74

 חיצוניים

0.74

qrstuvwxyz

0.73

ValueStyle

0.73

Activations Density 0.369%