INDEX

Explanations

song titles lengths and times

This neuron responds to standalone numeric tokens (e.g. years, durations, counts) in the document.

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

منون

-0.88

]}$

-0.83

رم

-0.82



-0.80

ignen

-0.80

⌊

-0.79

غی

-0.79

 gastronomía

-0.77

 pesados

-0.77

*}$

-0.77

POSITIVE LOGITS

↵↵↵↵↵↵↵↵↵

1.08

↵↵↵↵

1.05

↵

1.02

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.00

↵↵↵

1.00

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.00

↵↵↵↵↵↵↵↵↵↵

0.99

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.98

↵↵↵↵↵

0.96

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.95

Activations Density 0.425%