INDEX

Explanations

Growth

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

OGND

-0.77

+#+#

-0.68

 ویکی‌پدیای

-0.65

хьтан

-0.63

vician

-0.62

labus

-0.60

ütten

-0.60

HEET

-0.59

affaire

-0.57

 LUMP

-0.57

POSITIVE LOGITS

BeginContext

0.53

 rings

0.51

 areas

0.47

jaran

0.47

ringar

0.47

of

0.47

 water

0.47

 goals

0.46

ringen

0.45

 onto

0.44

Activations Density 0.045%