INDEX

Explanations

measure space operations

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

end

-1.13

做出

-1.05

🫶

-1.04

\\

-1.03

InstrumentedTest

-0.97

\$

-0.97

污染

-0.96

胸口

-0.95

作出

-0.93

 towering

-0.93

POSITIVE LOGITS

 Könige

1.16

vaná

1.13

一张

1.11

Bukan

1.05

 there

1.03

Really

1.02

されてる

1.02

 planas

1.02

banyak

1.02

pantal

1.02

Activations Density 0.012%