INDEX

Explanations

mathematical expressions

This neuron detects tokens that are part of mathematical expressions—especially variable names, subscripts, and other inline math symbols.

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

of

-2.20

 have

-1.80

</strong>

-1.77

 will

-1.71

at

-1.68

</h1>

-1.59

if

-1.59

 kept

-1.56

 consultato

-1.52

 ones

-1.51

POSITIVE LOGITS

 certaines

1.84

 temperat

1.62

鉭

1.57

ebly

1.57

硨

1.56

~~~~~~~

1.55

蓠

1.55

刄

1.54

≦

1.53

✓

1.48

Activations Density 0.044%