INDEX

Explanations

following common English words

The neuron fires on the main topical or content‐bearing words in a sentence—i.e. the key nouns or verbs that carry the document’s primary subject.

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

its

-1.38

 situé

-1.38

 always

-1.38

actéristi

-1.33

 anticipo

-1.32

 have

-1.27

 sempre

-1.25

led

-1.25

as

-1.24

it

-1.23

POSITIVE LOGITS

but

1.52

ṁ

1.38

 निम्नलिखित

1.38

𝟏

1.31

and

1.31

 hoge

1.30

endfor

1.27

 články

1.26

one

1.23

mö

1.20

Activations Density 0.090%