INDEX

Explanations

calls police on

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

aimeJ

-1.39

 męski

-1.38

{$\

-1.38

 there

-1.33

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.32

くらいで

-1.32

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.31

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.29

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.28

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.28

POSITIVE LOGITS

one

1.87

 like

1.78

類似

1.37

 himself

1.36

 from

1.35

who

1.34

has

1.34

 allows

1.33

 adds

1.32

 comparable

1.30

Activations Density 0.366%