INDEX

Explanations

names and references

The neuron strongly activates on the opening parenthesis of inline citations or reference markers (e.g. “(John 3:16)”).

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

You

-2.14

Those

-2.03

What

-1.87

Dentro

-1.84

Its

-1.66

Всё

-1.65

That

-1.60

の概要

-1.60

显然

-1.59

それが

-1.58

POSITIVE LOGITS

in

1.70

 discussion

1.56

'';

1.43

an

1.38

Lia

1.35

and

1.31

1.30

서는

1.28

the

1.27

↵

1.27

Activations Density 0.021%