INDEX

Explanations

defeats and scores

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endra

-0.22

{{{

-0.19

iami

-0.18

omic

-0.18

åľ¨åĽ½åĨħ

-0.18

OOT

-0.17

ãģĿãģĹãģ¦

-0.17

æīĵéĢł

-0.17

uary

-0.17

Station

-0.17

POSITIVE LOGITS

èĥľè´Ł

0.24

Ã±e

0.23

çī¹åĪ«å£°æĺİ

0.22

ä½¿çĶ¨ç¶²è·¯

0.22

åĪ©äºİ

0.21

è¿ĻéĩĮæľī

0.21

åĬ¨çĶŁæĪĲ

0.20

æķĳæĬ¤è½¦

0.20

æī¿æĭħè´£ä»»

0.20

ä¸ºåķ¥

0.20

Activations Density 0.003%