INDEX

Explanations

Mad

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

 AssemblyCulture

-0.57

المناصب

-0.54

ValueGeneration

-0.49

клопе

-0.49

pidou

-0.47

 Coupé

-0.46

ceaux

-0.46

 côte

-0.45

Hozzáférés

-0.45

ętr

-0.45

POSITIVE LOGITS

hu

0.47

0.43

hi

0.41

patra

0.41

bh

0.40

hash

0.40

 pohon

0.40

 désol

0.40

 initComponents

0.39

hani

0.39

Activations Density 0.050%