INDEX

Explanations

6, 0, 2, 1

The neuron activates on standalone numeric tokens—counts, measurements, or decimal values.

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

estern

-1.16

).—

-1.15

 again

-1.13

sians

-1.10

Também

-1.09

𝜙

-1.09

cember

-1.09

ervant

-1.08

WHEREAS

-1.07

CCN

-1.06

POSITIVE LOGITS

 män

1.12

 with

1.09

of

1.07

in

1.05

 آذر

1.02

該当

1.02

 ваше

1.02

 termen

1.01

 کیلو

0.96

íc

0.95

Activations Density 0.001%