INDEX

Explanations

dates and numbers

The neuron fires on standalone numeric tokens (digits and multi‐digit numbers), i.e. it identifies numbers 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

 that

-1.48

 other

-1.29

of

-1.29

 only

-1.15

 from

-1.15

on

-1.11

 there

-1.10

one

-1.09

at

-1.07

 using

-1.07

POSITIVE LOGITS

 trám

1.25

 dán

1.23

regler

1.20

獷

1.16

inerja

1.14

 rám

1.12

顔が

1.12

 😁

1.11

ILDREN

1.10

𓆏

1.08

Activations Density 0.045%