INDEX

Explanations

status, process after noun

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

Даже

-1.52

 véhicule

-1.50

严重的

-1.35

 zarówno

-1.34

neces

-1.33

 chré

-1.31

Веду

-1.29

Более

-1.27

 défa

-1.27

 fonctionnent

-1.27

POSITIVE LOGITS

for

2.58

of

2.05

so

1.68

to

1.66

 should

1.59

了不少

1.49

 from

1.46

 will

1.41

 September

1.40

 before

1.37

Activations Density 0.043%