INDEX

Explanations

Non-English words

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

uktur

-0.50

 Pills

-0.47

TagHelper

-0.47

APIS

-0.47

 Knut

-0.47

 Kuli

-0.47

iau

-0.46

 tabled

-0.46

Tak

-0.46

TY

-0.46

POSITIVE LOGITS

 незавершена

0.90

Tikang

0.84

ViewFeatures

0.78

 Савезне

0.76

 محفوظة

0.71

AddTagHelper

0.69

 صوتيه

0.66

CppMethod

0.65

IsContent

0.64

 للمعارف

0.64

Activations Density 0.005%