INDEX

Explanations

indefinite article followed by noun or adjective

The neuron strongly activates on English indefinite articles (“a” and “an,” and to a lesser extent “all”).

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

-2.09

-1.91

 relacionado

-1.70

いかがでしょうか

-1.60

なのに

-1.54

you

-1.45

-1.44

に来て

-1.43

 know

-1.41

 ‘‘

-1.38

POSITIVE LOGITS

賸

1.60

⤞

1.54

 perioden

1.50

 from

1.49

 花卉

1.45

🏢

1.44

 canadi

1.41

絰

1.40

ocracy

1.39

omania

1.39

Activations Density 0.071%