INDEX

Explanations

announced or debated action

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

 from

-1.52

 they

-1.38

 maaf

-1.33

 then

-1.26

());

-1.24

ׇ

-1.20

 pribadi

-1.17

 тогда

-1.16

 tramont

-1.16

 توانند

-1.13

POSITIVE LOGITS

its

2.28

Its

1.37

וּ

1.36

ּוֹ

1.23

 Políticas

1.22

 announced

1.21

 terá

1.13

has

1.11

 itself

1.10

将其

1.09

Activations Density 0.049%