INDEX

Explanations

When verbs are followed by specific words

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

by

-1.65

who

-1.65

﹍﹍

-1.60

and

-1.51

 adalah

-1.34

 έχουν

-1.34

if

-1.32

 Hauptstadt

-1.31

 also

-1.30

 would

-1.27

POSITIVE LOGITS

or

1.59

 например

1.51

ことがあります

1.44

stache

1.42

 Selain

1.38

 innymi

1.38

ícias

1.33

givings

1.30

 determinados

1.30

 других

1.29

Activations Density 0.662%