INDEX

Explanations

researcher

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

 المعيارى

-0.69

 wireType

-0.68

SharedDtor

-0.66

 Wicidata

-0.65

 ويكيپيديا

-0.63

RTEE

-0.63

 Normdatei

-0.62

 castes

-0.61

رشف

-0.61

 houſe

-0.61

POSITIVE LOGITS

at

0.51

Ann

0.49

are

0.49

ುತ್ತ

0.48

ท้าย

0.46

 said

0.45

شة

0.44

racuse

0.43

beleid

0.43

Ann

0.43

Activations Density 0.017%