INDEX

Explanations

help

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

to

-0.90

 estekak

-0.81

HomeAsUpEnabled

-0.69

UnusedPrivate

-0.64

tagext

-0.60

Hozzáférés

-0.60

 useState

-0.58

withOpacity

-0.58

useState

-0.55

providedIn

-0.55

POSITIVE LOGITS

 maux

0.56

 Turns

0.51

TUM

0.49

 realising

0.49

It

0.48

PreferredItem

0.47

Its

0.46

cuba

0.45

ulets

0.45

 chi̍t

0.44

Activations Density 0.021%