INDEX

Explanations

integer assignment

The neuron mainly activates on numeric tokens (including integers and floating‐point numbers) in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

('')

0.65

 enige

0.64

())

0.60

 {}'.

0.59

 qualquer

0.57

 அம்

0.55

('/')

0.55

 {}".

0.53

 দিয়ে

0.52

 যেকোন

0.52

POSITIVE LOGITS

"",

1.27

({},

1.26

("",

1.15

*,

1.14

{},

1.13

++,

1.13

?,?,

1.13

{},

1.11

$,

1.11

 ',',

1.09

Activations Density 0.015%