INDEX

Explanations

code identifiers and definitions

The neuron spikes on title‐style or identifier tokens—i.e. words in TitleCase or ALL-Caps that serve as section headings, class/function names, or other code identifiers.

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

-1.70

but

-1.57

!*\

-1.55

 memiliki

-1.37

άνει

-1.33

=");

-1.32

برة

-1.30

 sekitar

-1.28

 "}";

-1.27

veloper

-1.25

POSITIVE LOGITS

1.66

 außerdem

1.45

 zudem

1.42

 baratas

1.26

 réalisées

1.24

 ibang

1.21

 armé

1.21

 chileno

1.19

 anderer

1.16

除此之外

1.16

Activations Density 0.197%