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

 Paglinawan

-0.91

 kasarigan

-0.87

 CreateTagHelper

-0.81

KommentareTeilen

-0.79

 AssemblyCulture

-0.79

EndContext

-0.77

ArgsConstructor

-0.77

 الحره

-0.74

ंदीखरीदारी

-0.74

oa̍t

-0.73

POSITIVE LOGITS

 board

0.49

 LUMP

0.45

mobileqq

0.39

mes

0.38

nes

0.37

ils

0.35

me

0.35

tagext

0.33

Measured

0.32

Noi

0.32

Activations Density 0.008%

No Known Activations