INDEX

Explanations

numbers or references to studies or names in parentheses, especially those involving a hyphen

Hyphen

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

 سكانية

-0.68

Efq

-0.66

 ―――――

-0.63

lorette

-0.60

axaca

-0.60

TPA

-0.59

 myſelf

-0.57

ervant

-0.56

 raiſ

-0.56

 itſelf

-0.56

POSITIVE LOGITS

0.54

—

0.53

.”

0.52

--

0.49

($

0.48

–

0.47

--$

0.46

.’

0.45

,$

0.45

’.

0.44

Activations Density 5.272%