INDEX

Explanations

question starters

The neuron fires on English pronouns and demonstratives (e.g., “this,” “it,” “they”) and related auxiliary words.

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

 various

-1.64

 many

-1.37

 such

-1.37

 cuaca

-1.21

 reduzieren

-1.21

 those

-1.20

jenigen

-1.20

 bertambah

-1.20

 maggior

-1.20

 include

-1.18

POSITIVE LOGITS

but

1.38

了不少

1.37

了些

1.30

1.23

いましたが

1.21

мулятор

1.17

踮

1.16

 utilizado

1.15

足够的

1.13

特殊的

1.09

Activations Density 0.230%