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

клопе

-0.89

 متعلقه

-0.81

ftagPool

-0.78

 yaml

-0.73

findpost

-0.71

 transfieras

-0.68

TagHelper

-0.65

 resourceCulture

-0.64

yml

-0.64

fml

-0.63

POSITIVE LOGITS

 word

0.59

word

0.49

 WORD

0.47

MS

0.43

 Word

0.41

Word

0.40

Ms

0.40

odor

0.36

 POWERS

0.35

zor

0.34

Activations Density 0.000%

No Known Activations