INDEX

Explanations

mathematical notation with variables

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

of

-2.00

and

-1.54

 reconoc

-1.31

らを

-1.29

-1.23

era

-1.19

らが

-1.19

 gewel

-1.19

termine

-1.17

lili

-1.16

POSITIVE LOGITS

 when

1.69

 because

1.56

when

1.53

quando

1.49

if

1.45

现在

1.38

这

1.37

这个

1.35

 тільки

1.34

 töd

1.34

Activations Density 0.106%