INDEX

Explanations

hishishis

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

in

-1.20

 before

-1.20

świ

-1.16

 Архиви

-1.11

 грудня

-1.10

 квітня

-1.09

for

-1.09

ּוֹ

-1.07

 fotografico

-1.07

on

-1.05

POSITIVE LOGITS

一路

1.29

 especially

1.25

particularly

1.23

uſ

1.20

 cependant

1.17

considering

1.15

 garrafa

1.15

 estadia

1.13

controle

1.13

mì

1.13

Activations Density 0.017%