INDEX

Explanations

function return descriptions

The neuron responds to numeric tokens, especially floating‐point numbers (decimal values).

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

</span>

0.71

`;

0.65

</img>

0.60

`,`

0.59

`,

0.57

cdots

0.56

$--

0.56

¬

0.55

｣

0.54

*-

0.53

POSITIVE LOGITS

<blockquote>

3.52

1.61

[]

1.42

[]

1.34

$$\

1.20

$$\

1.19

1.18

[]=

1.06

[],

1.04

Activations Density 0.075%