INDEX

Explanations

The neuron fires on tokens that are floating‐point numbers (decimal numeric values).

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

 Mein

0.77

0.75

aunque

0.75

eous

0.74

 atheist

0.74

eo

0.73

即便

0.73

et

0.73

рые

0.73

POSITIVE LOGITS

.’”

0.77

আগ

0.75

Το

0.75

चलिए

0.74

 તો

0.74

ToUpper

0.74

 สำหรับ

0.73

 liné

0.72

 ผ้า

0.72

Გ

0.72

Activations Density 0.000%