INDEX

Explanations

planning for

This neuron activates on numeric tokens representing large floating‐point values (e.g., numbers with decimal points in the thousands).

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

 случаях

0.82

 कल्चर

0.75

 हमको

0.75

 posteriores

0.75

 Nachdem

0.75

 Кроме

0.74

ⅼ

0.73

Woh

0.72

 تقريبا

0.72

 Даже

0.71

POSITIVE LOGITS

审

0.75

没有

0.74

监

0.74

负

0.74

颜

0.73

弯

0.72

答案

0.71

步骤

0.70

ابع

0.69

一个人

0.69

Activations Density 0.001%