INDEX

Explanations

actions and their descriptions

idiomatic phrases and puns, particularly those using figurative or playful language.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

to

-1.69

seems

-1.38

 cristianos

-1.34

 какие

-1.20

 azeite

-1.19

『

-1.18

those

-1.16

 roze

-1.15

婠

-1.14



-1.13

POSITIVE LOGITS

two

1.29

uma

1.25

1.23

Mosa

1.21

Fitment

1.19

袴

1.18

 ferroviaire

1.16

 作り方

1.15

Ведущий

1.15

 oust

1.14

Activations Density 0.224%