INDEX

Explanations

Maxim name, Latin, code punctuation

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

for

-1.40

 then

-1.36

all

-1.25

 Only

-1.22

 only

-1.20

to

-1.18

翳

-1.13

海岸

-1.13

 два

-1.06

 caminhada

-1.02

POSITIVE LOGITS

釹

1.32

you

1.28

ܣ

1.27

 μας

1.20

 musíte

1.19

 خواهید

1.18

our

1.16

pantalones

1.13

eció

1.13

 tivi

1.13

Activations Density 0.000%

No Known Activations