INDEX

Explanations

non- states or participation

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

â

-1.45

geſ

-1.41

மே

-1.39

 lidé

-1.38

 температуре

-1.38

 policiales

-1.38

更为

-1.37

 вовсе

-1.37

ன்று

-1.37

Moreover

-1.37

POSITIVE LOGITS

for

1.49

not

1.43

 affinch

1.38

1.36

 cœurs

1.34

🛇

1.33

1.30

ệu

1.30

 می‌شوند

1.29

essment

1.25

Activations Density 0.040%