INDEX

Explanations

mathematical notation likemathbf m

The neuron activates on numeric constants (digits and numbers) within scientific or mathematical notation.

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

if

-1.90

 แต่

-1.80

いつ

-1.80

-1.66

 coloridas

-1.64

成了

-1.63

もありました

-1.61

долго

-1.58

 ricas

-1.58

 brancas

-1.57

POSITIVE LOGITS

薮

1.91

 XNUMX

1.88

</h2>

1.88

chestra

1.84

槙

1.80

1.78

phans

1.77

ments

1.77

蓼

1.75

lihood

1.74

Activations Density 0.081%