INDEX

Explanations

required by

This neuron fires on formal license‐and legal‐boilerplate language (e.g. “licensed under,” “unless required by applicable law,” license URLs, 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

 malgré

-1.63

 största

-1.57

 cial

-1.52

 menthe

-1.52

;(

-1.50



-1.49

ditionally

-1.48

 dieu

-1.48

都已经

-1.46

 ular

-1.46

POSITIVE LOGITS

at

2.64

by

2.42

and

2.14

as

1.95

or

1.84

 There

1.73

 there

1.66

 seemed

1.64

 epitom

1.63

one

1.59

Activations Density 0.282%