INDEX

Explanations

first name and last name

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

for

-1.23

getCause

-1.14

↵↵

-1.05

lO

-1.05

 kunst

-1.03

<0xF4>

-1.03

Minus

-1.03

DDDD

-1.02

mą

-1.02

 deles

-1.01

POSITIVE LOGITS

我对

1.30

 name

1.29

 emphasised

1.23

 Ее

1.22

órc

1.20

忾

1.17

了一遍

1.17

uerdo

1.16

 ändert

1.15

 tilbud

1.14

Activations Density 0.006%