INDEX

Explanations

learning and explaining

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

புக

0.69

 ermöglichen

0.68

훅

0.66

 povol

0.66

പ്പിക്ക

0.64

 stroj

0.63

ൃശ

0.63

 сни

0.63

 ermöglicht

0.63

 grantor

0.62

POSITIVE LOGITS

 recited

1.23

 memorize

1.20

 recite

1.19

 practiced

1.18

 practicing

1.17

 practice

1.16

 practised

1.16

 practise

1.15

 reciting

1.13

 completing

1.11

Activations Density 0.440%