INDEX

Explanations

years, seasons, decade, until

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

å·²ç»ıè¢«

-0.10

ä¹Łä¸įä¾ĭå¤ĸ

-0.10

æĹ©å°±

-0.09

ä¹ŁåºĶè¯¥

-0.09

æĹ©åľ¨

-0.09

æĹ©å·²

-0.08

ä½łçİ°åľ¨

-0.08

æ°¸è¿ľ

-0.08

ä»»ä½ķå½¢å¼ı

-0.08

æĽ´è¦ģ

-0.08

POSITIVE LOGITS

çĽ´åĪ°

0.20

çĽ´èĩ³

0.19

_until

0.17

 until

0.17

Until

0.17

until

0.16

 Until

0.16

ä¸ĢçĽ´åĪ°

0.16

à¸Īà¸Ļ

0.16

 jusqu

0.13

Activations Density 0.110%

No Known Activations