INDEX

Explanations

code imports and declarations

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

 ifølge

-1.34

 særlig

-1.32

 that

-1.31

皤

-1.30

-1.27

to

-1.24

 тези

-1.23

 хорошая

-1.18

 faktisk

-1.17

elegante

-1.17

POSITIVE LOGITS

 ihrer

1.90

ítez

1.74

 them

1.52

ربای

1.41

 ihres

1.41

酝

1.41

roffene

1.40

に於

1.40

 их

1.37

之时

1.32

Activations Density 0.016%