INDEX

Explanations

things that existed

The neuron detects words and phrases expressing the realization or discovery that something exists (e.g. “existed,” “exists,” “I didn’t even know,” “I had no idea”).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 first

-1.20

 while

-1.19

 that

-1.16

 sappi

-1.09

 laurel

-1.04

 lupo

-1.03

ما

-1.02

ahu

-1.00

号

-0.99

vação

-0.98

POSITIVE LOGITS

こんなに

1.45

still

1.34

匂

1.28

 wonderful

1.27

そも

1.25

eight

1.24

 coloridas

1.24

躾

1.23

おかしい

1.23

 rojos

1.22

Activations Density 0.070%