INDEX

Explanations

numbers and currency symbols

The neuron is keyed to numeral tokens (digits), i.e. occurrences of numbers (like years, ages, dates) in the text.

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

ло

-0.79

 olie

-0.78

 Witches

-0.76

subplot

-0.76

 теперь

-0.75

now

-0.73

 женские

-0.73

 лучшие

-0.73

టి

-0.73

ді

-0.72

POSITIVE LOGITS

Forgotten

0.80

Fox

0.76

Leisure

0.75

པ

0.75

 menurun

0.75

Tog

0.74

fox

0.73

Argumento

0.73

谆

0.73

 refresh

0.72

Activations Density 0.014%