INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.85

InjectAttribute

-0.79

 beginnetje

-0.69

 <=",

-0.67

 Roskov

-0.66

 Мексичка

-0.66

RegistryLite

-0.66

IsContent

-0.65

NKC

-0.64

 مرئيه

-0.63

POSITIVE LOGITS

seamnă

0.50

toBeTruthy

0.47

 Tema

0.46

streng

0.45

tower

0.44

νομα

0.44

سياسي

0.43

atimes

0.42

humanité

0.41

Tema

0.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.