INDEX

Explanations

declarative phrases and questions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ۢ

-1.11

 kond

-1.00

Şi

-0.95

 akku

-0.94

 kriminal

-0.91

 bakter

-0.87

esserts

-0.87

 desmotiv

-0.86

凄く

-0.86

 teka

-0.85

POSITIVE LOGITS

ölk

1.13

1.12

 zahr

1.06

1.00

gham

0.99

FAS

0.97

SCE

0.94

﴿

0.93

ferrer

0.93

 роки

0.91

Activations Density 0.006%