INDEX

Explanations

if you

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

 declarat

-1.55

 ziemlich

-1.47

 手绘

-1.36

 falschen

-1.32

 vermutlich

-1.32

 möglicherweise

-1.24

 wahrscheinlich

-1.23

料

-1.21

}=\

-1.21

astră

-1.18

POSITIVE LOGITS

</strong>

1.59

any

1.51

amaño

1.49

記入

1.35

brano

1.29

有什麼

1.26

 dont

1.23

carnated

1.23

jabat

1.22

sistence

1.20

Activations Density 0.042%