INDEX

Explanations

prior art, United States, public access, desk, century

The neuron strongly lights up on uncommon, content-bearing words (i.e. low-frequency, domain-specific tokens) rather than on common function 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

you

-1.63

鹮

-1.44

okość

-1.31

Fig

-1.28

estão

-1.24

appspot

-1.23

cjonal

-1.20

 pengunjung

-1.20

It

-1.19

POSITIVE LOGITS



1.49

⛦

1.41

 vieles

1.33

 tacón

1.33

绛

1.31

 servis

1.27

 navide

1.27

änemark

1.25

 wundersch

1.22

焢

1.21

Activations Density 0.702%