INDEX

Explanations

text enclosed in angle brackets

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

No Comments

Negative Logits

 NDEBUG

-0.94

 autorytatywna

-0.93

 Normdatei

-0.84

).__

-0.81

ConstraintMaker

-0.79

 hunne

-0.77

 enfans

-0.77

+#+#

-0.76

!(:

-0.72

formik

-0.71

POSITIVE LOGITS

↵

0.45

 شر

0.43

tot

0.42

urie

0.42

unders

0.41

شو

0.40

chom

0.40

 cabins

0.40

cima

0.40

doc

0.39

Activations Density 0.019%