INDEX

Explanations

proper nouns and specific concepts

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

imli

-1.48

 zoals

-1.45

нув

-1.34

 bahç

-1.32

for

-1.18

чя

-1.17

 mainstay

-1.16

 they

-1.16

of

-1.15

റെ

-1.13

POSITIVE LOGITS

posited

1.17

某些

1.15

 diejenigen

1.09

っちゃった

1.05

 anybody

1.04

 keinerlei

1.04

出的

1.03

禧

1.02

有很多

1.02

 currently

1.01

Activations Density 0.273%