INDEX

Explanations

processes and data

The neuron detects floating‐point numeric tokens (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

Negative Logits

 Jokes

0.86

 Diagnostics

0.85

 Problems

0.84

 Books

0.82

 Detect

0.82

 Plots

0.80

 Politics

0.79

 Poetry

0.78

 Opinions

0.78

 Docs

0.77

POSITIVE LOGITS

кает

0.88

მასრულ

0.86

 indígen

0.86

क

0.85

 нагру

0.85

 രക്ഷ

0.85

 khái

0.84

 তেমনই

0.83

 пусть

0.81

 atmosfé

0.81

Activations Density 0.000%