INDEX

Explanations

The neuron is tuned to pick out numeric tokens—especially digits used as stoichiometric coefficients or subscripts/superscripts in chemical formulas and reaction equations.

numbers, quantities, and scientific terms

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

two

-1.24

ísimas

-1.20

なども

-1.16

-1.15

if

-1.12

などを

-1.12

などは

-1.08

 will

-1.07

 registrado

-1.02

 function

-0.97

POSITIVE LOGITS

of

1.36

 pitié

1.30

 démocr

1.23

Wasn

1.23

航

1.17

 fiyat

1.15

Histology

1.15

értel

1.09

 oídos

1.07

szám

1.06

Activations Density 0.011%