INDEX

Explanations

Careful

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

Careful

-0.79

 Careful

-0.71

éramos

-0.50

تیب

-0.45

thodoxy

-0.44

retts

-0.44

quatch

-0.43

tiness

-0.42

 Roskov

-0.42

Bronnen

-0.41

POSITIVE LOGITS

of

0.62

Бахар

0.60

 Вікіпе

0.59

FunctionFlags

0.57

 with

0.56

KommentareTeilen

0.56

ftest

0.55

 éditoriale

0.54

 onCancelled

0.54

to

0.54

Activations Density 0.008%