INDEX

Explanations

saying something positive

disclaimer caveat warning preface

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ीडी

0.40

াজে

0.39

を集

0.39

 समानार्थी

0.38

詳しい

0.37

 دارید

0.37

 étudié

0.37

 verändert

0.37

 avulla

0.37

自分で

0.37

POSITIVE LOGITS

 mention

1.53

say

1.47

 reiterate

1.34

mention

1.24

say

1.23

 emphasize

1.22

 Mention

1.19

 emphasise

1.19

 сказать

1.18

 note

1.15

Activations Density 0.244%