INDEX

Explanations

math and code structures

The neuron is specialized in spotting numeric literals (stand‐alone numbers) in code or 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

 then

-1.06

。『

-1.04

諳

-1.02

 wtedy

-0.98

if

-0.96

asjon

-0.96

 while

-0.95

ilities

-0.94

[].

-0.90

setCellValue

-0.89

POSITIVE LOGITS

"",

1.34

 Перейти

1.34

'',

1.14

Chloroform

1.11

$,

1.09

 '*',

1.05

\%,

1.03

 '-',

1.02

to

1.02

%,

1.00

Activations Density 0.012%