INDEX

Explanations

The neuron fires on numeric tokens representing measured or statistical values—especially floating‐point numbers with decimal points.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 microturbulence

0.70

 microorganism

0.67

 homomorphism

0.66

 microorganisms

0.64

 renormalization

0.63

 proporción

0.63

 eukaryotic

0.62

 nonparametric

0.62

 cuánt

0.61

 سه

0.61

POSITIVE LOGITS

 range

1.00

 ranges

0.88

range

0.86

 Range

0.85

 ranged

0.85

 dramatically

0.84

 varies

0.82

 vastly

0.82

ranges

0.80

Range

0.77

Activations Density 0.005%