INDEX

Explanations

references to 'our' and 'the' and 'we' and 'us'

our

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

WaitGroup

-0.68

########.

-0.65

 ours

-0.63

ours

-0.60

our

-0.57

 nôtre

-0.55

 שלנו

-0.55

 Ours

-0.54

our

-0.53

 externi

-0.52

POSITIVE LOGITS

 favorite

0.53

+#+#

0.51

::__

0.50

riad

0.50

 objective

0.49

 preferred

0.48

 hành

0.47

Itoa

0.46

 work

0.46

 Préférences

0.45

Activations Density 10.401%