INDEX

Explanations

as is agreement

This neuron fires on boilerplate license‐and‐copyright comment text (e.g. words like “file,” “license,” “we’re willing to,” “distributed,” 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

at

-1.56

 without

-1.52

or

-1.45

 provides

-1.45

 provide

-1.41

 striving

-1.36

 steadily

-1.36

 during

-1.35

 should

-1.34

in

-1.33

POSITIVE LOGITS

 Dinas

1.43

 ſon

1.31

probably

1.30

 your

1.30



1.23

 goofy

1.21

 เว

1.20

 quirky

1.20

primarily

1.20

really

1.19

Activations Density 0.002%