INDEX

Explanations

questions seeking specific information

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

 même

-1.39

mô

-1.38

 dokonce

-1.32

 októ

-1.31

cisive

-1.30

sistent

-1.30

its

-1.30

 sucul

-1.30

tadır

-1.26

giai

-1.26

POSITIVE LOGITS

of

1.53

1.36

1.30

 crime

1.24

 then

1.24

1.23

1.22

 daugiau

1.20

 kupić

1.20

for

1.16

Activations Density 0.084%