INDEX

Explanations

variable names and code identifiers

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

for

-1.27

of

-1.23

and

-1.16

 other

-1.15

 which

-1.12

or

-1.09

-1.08

-1.05

POSITIVE LOGITS

킁

1.47

 notor

1.41

 Merdeka

1.41

 FANT

1.37

 prohi

1.35

 チラ

1.34

 DPRD

1.26

 supli

1.25

 Faso

1.23

 家居

1.22

Activations Density 0.006%