INDEX

Explanations

STR followed by number or Re

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

reb

-0.08

bol

-0.07

çļĦåı¯

-0.07

upo

-0.07

otr

-0.07

LIKELY

-0.06

æĥĨæĢħ

-0.06

hov

-0.06

ä»Ģä¹Īéĥ½ä¸į

-0.06

ieber

-0.06

POSITIVE LOGITS

å¿ĥåľ°

0.07

åĽ±

0.07

èŀįèŀį

0.07

 máº¡o

0.07

toff

0.07

å®ŀæĸ½æĸ¹å¼ı

0.07

irsch

0.07

Ð°Ð½ÑĤÐ°

0.07

prises

0.06

illian

0.06

Activations Density 0.023%