INDEX

Explanations

states of affairs

The neuron flags abstract nouns (e.g. “phenomenon,” “fact,” “practice,” “situation,” etc.) that serve to label or introduce key findings or claims in scientific or formal text.

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

and

-1.57

 genieten

-1.33

intenant

-1.30

 aussieht

-1.22

änderung

-1.20

 lidé

-1.17

 dámské

-1.17

škoda

-1.13

vky

-1.13

と話

-1.13

POSITIVE LOGITS

«

1.45

«

1.35

1.17

1.12

…

1.12

1.10

—

1.10

/*

1.09

—

1.09

»

1.07

Activations Density 0.060%