INDEX

Explanations

interjections with punctuation interspersed in text

ellipses

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

Negative Logits

...

-0.73

NewUrlParser

-0.70

,...

-0.67

…

-0.66

....

-0.65

 bParam

-0.65

-...

-0.64

...-

-0.63

...}

-0.63

...

-0.61

POSITIVE LOGITS

 juſ

0.57

if

0.56

 Geen

0.54

pis

0.53

 auffi

0.50

 reaſon

0.49

 ſtate

0.49

 Chriftian

0.48

does

0.47

 ſche

0.47

Activations Density 4.168%