INDEX

Explanations

explanation of code or instructions

This neuron fires on numeric tokens—years, dates, measurements, or other 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

 Yellowstone

0.86

學生

0.86

 aantal

0.85

 Перейти

0.85

 Диа

0.84

 другой

0.82

ง

0.82

Спољашње

0.81

 Mohan

0.81

 столь

0.81

POSITIVE LOGITS

デニム

0.74

تمل

0.71

 concreta

0.70

iffo

0.70

 networks

0.68

ನ್ನ

0.67

icits

0.67

ARE

0.66

ことになる

0.64

腴

0.64

Activations Density 0.001%