INDEX

Explanations

close, nearly, within

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

 Occasionally

-0.82

точник

-0.81

偶尔

-0.79

 zowel

-0.77

essor

-0.76

完毕

-0.76

主动

-0.75

 ocas

-0.75

普通的

-0.75

 afectadas

-0.75

POSITIVE LOGITS

 close

1.36

CLOSE

1.28

close

1.20

 almost

1.13

ใกล้

1.13

 nearly

1.10

 closely

1.08

 near

1.04

 certainly

1.02

 близ

1.02

Activations Density 0.058%