INDEX

Explanations

effects of weighted mean

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

brigens

-1.43

Terug

-1.35

 dzied

-1.34

Prijs

-1.32

 citas

-1.32

\\

-1.31

vocations

-1.30

᾿

-1.30

 chrétienne

-1.29

 כוס

-1.28

POSITIVE LOGITS

 then

2.16

for

1.52

ֶּ

1.43

ּוֹ

1.41

 before

1.34

dig

1.31

וֹ

1.26

憲法

1.26

 prior

1.25

 based

1.23

Activations Density 0.001%