INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 terdapat

0.20

<unused2121>

0.19

<0xE2>

0.17

 теркәлүсез

0.17

<unused2123>

0.17

 وذلك

0.17

obtained

0.16

 adlı

0.16

erdapat

0.16

itherto

0.16

POSITIVE LOGITS

 something

0.46

 things

0.45

 EVERYTHING

0.45

 them

0.42

 ANYTHING

0.41

 lots

0.39

 crappy

0.39

 everything

0.38

 stuff

0.38

 SOME

0.38

Activations Density 11.236%

No Known Activations