INDEX

Explanations

names like lucifer, michael, apost, exor

The neuron fires on proper names, titles, and other named-entity tokens (e.g. character names, show/movie/game titles, genus names, etc.).

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

 figliu

-1.44

 italienischen

-1.43

</h5>

-1.39

 objected

-1.38

 includes

-1.35

</h3>

-1.32

 consists

-1.30

 rinnov

-1.30

 adesi

-1.26

大概是

-1.24

POSITIVE LOGITS

of

1.52

 your

1.45

mathrm

1.30

Спа

1.22

 Przed

1.13

not

1.11

ların

1.10

จาก

1.08

all

1.07

вість

1.05

Activations Density 0.007%