INDEX

Explanations

field names, numbers, or codes

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 what

-1.91

 which

-1.66

</h4>

-1.37

 longtime

-1.30

We

-1.25

↵↵

-1.24

焄

-1.19

してみました

-1.16

 informasjon

-1.15

</h5>

-1.14

POSITIVE LOGITS

 mismos

1.50

 mett

1.46

е

1.39

1.34

1.32

});

1.29

 órganos

1.29

())),

1.28

嵓

1.28

))))

1.27

Activations Density 0.123%

No Known Activations