INDEX

Explanations

a group of

The neuron fires when it sees numeric counts—especially in “group of [number]” constructions indicating the size of a group.

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

𓆜

-2.70

鳊

-2.27

 aussit

-2.20

鱘

-2.20

戆

-2.17

鸱

-2.16

tubes

-2.16

༷

-2.14

 взгля

-2.13

𓋼

-2.09

POSITIVE LOGITS

 siendo

2.20

 comprising

2.13

 encompassing

2.09

of

2.09

clés

2.08

ieteur

2.06

 которого

2.05

 Consequently

2.05

or

2.03

 και

2.02

Activations Density 0.018%