INDEX

Explanations

specific word followed by a specific word

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

so

-1.41

our

-1.25

𝗺

-1.23

we

-1.16

 більш

-1.16

 парла

-1.12

 додат

-1.10

 इसमें

-1.09

 each

-1.08

 those

-1.05

POSITIVE LOGITS

🩹

1.47

饪

1.23

virano

1.23

🧫

1.20

 merve

1.19

 (!__

1.18

 alho

1.18

以上就是

1.17

おわりに

1.17

zdě

1.17

Activations Density 0.003%