INDEX

Explanations

Introduce general statements

The neuron detects generalizing adverbs (like “typically,” “generally,” “usually”) that introduce broad statements.

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

-2.63

or

-1.76

is

-1.61

 نهاية

-1.48

了她

-1.43

atação

-1.43

ਥ

-1.42

 пър

-1.41

moiselle

-1.39

nteral

-1.38

POSITIVE LOGITS

of

1.91

 these

1.77

相比

1.69

这是一

1.55

 this

1.52

 pensato

1.48

 About

1.47

it

1.45

we

1.45

 there

1.45

Activations Density 0.024%