INDEX

Explanations

section

The neuron is detecting numeric tokens (digits and numbers) in the text.

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

 वस्तू

0.74

Puede

0.72

Ха

0.71

驃

0.69

िशा

0.68

或者是

0.67

 Atau

0.65

0.64

Metall

0.63

POSITIVE LOGITS

 crucially

0.65

 debacle

0.64

 syarat

0.63

 criteria

0.61

 помнить

0.61

 explicado

0.60

 algorithm

0.60

 expliquer

0.60

 fiasco

0.60

Activations Density 0.289%