INDEX

Explanations

listing

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

ãĬĹ

-0.23

åµ¯

-0.23

æ®Ĵ

-0.23

à¸Ħà¸ĵà¸°à¸ģà¸£à¸£à¸¡

-0.23

à¹Ģà¸Ĺà¸¨à¸ģà¸²

-0.22

ä¸ķ

-0.22

à¹Ģà¸¨à¸£à¸©

-0.22

à¸Ńà¸³à¸Ļà¸§à¸¢à¸Ħà¸§à¸²à¸¡

-0.22

à¸ªà¹Ĥà¸¡

-0.21

 Erotische

-0.21

POSITIVE LOGITS

èĳĹåĲįçļĦ

0.28

 ones

0.26

çŁ¥åĲįçļĦ

0.23

çļĦèº«å½±

0.22

ä½Ĩä¸įéĻĲäºİ

0.20

à¸ªà¸Ńà¸ĩ

0.20

éĩĿå°į

0.20

ä¸Ģä¸ªæĺ¯

0.20

ones

0.20

ãĢĬ

0.20

Activations Density 0.164%