INDEX

Explanations

one or some of

This neuron lights up on generic quantifier phrases that introduce an item or point (e.g. “one thing,” “some things,” “few things,” “one resource”).

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

就被

-1.45

следования

-1.30

lių

-1.23

 müßte

-1.20

 витра

-1.19

 皇族

-1.16

 gratuite

-1.14

 ótima

-1.14

 тоже

-1.14

is

-1.14

POSITIVE LOGITS

 that

2.89

you

2.53

we

1.99

1.91

 would

1.70

 your

1.62

それでは

1.54

 myself

1.48

必须要

1.44

my

1.42

Activations Density 0.040%