INDEX

Explanations

activities and events

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

 there

-1.69

</b>

-1.34

 tačiau

-1.30

 this

-1.27

 everything

-1.22

 todėl

-1.18

 they

-1.16

 what

-1.14

 then

-1.12

 cambiare

-1.10

POSITIVE LOGITS

</h3>

1.65

↵↵

1.45

'\\

1.27

镲

1.23

for

1.22

arse

1.21

 могат

1.16

试试

1.14

try

1.13

 nervously

1.13

Activations Density 0.048%