INDEX

Explanations

season, overall, affecting

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

zos

-0.25

åĨ¤

-0.24

æ¢°

-0.24

zÃ¡

-0.23

æĶ¿æ²»

-0.23

çīµ

-0.23

å®¿

-0.22

è¡ĮæĶ¿éĥ¨éĹ¨

-0.22

åĪĨå¼Ģ

-0.22

æĪĸå¤ļ

-0.22

POSITIVE LOGITS

 cumulative

0.36

ç´¯ç§¯

0.35

æĪªèĩ³çĽ®åīį

0.28

å·²è¾¾

0.28

ç´¯è®¡

0.28

æ¯Ķä¸Ĭå¹´

0.28

è¶Ĭé«ĺ

0.28

 acum

0.28

 totals

0.27

 overall

0.26

Activations Density 0.013%