INDEX

Explanations

Code and inventions

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

InvalidProtocol

-0.70

RTEE

-0.60

γή

-0.53

 ویکی‌پدی

-0.50

醐

-0.48

atists

-0.47

 Allianz

-0.46

 않는

-0.45

cism

-0.45

 appelez

-0.45

POSITIVE LOGITS

Tikang

0.57

thor

0.57

HomeAsUpEnabled

0.55

bar

0.54

AxisAlignment

0.52

 backwards

0.51

 wedi

0.51

 frigo

0.50

 backward

0.49

EDEFAULT

0.48

Activations Density 0.076%