INDEX

Explanations

outpost troopers Amtrak anomaly

The neuron strongly activates on references to uniformed military or law-enforcement units and their posts.

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

ться

-2.50

 新款

-2.20

ၜ

-2.17

轻声

-2.03

浿

-1.97

ouvrir

-1.95

廍

-1.93

颙

-1.92



-1.92

::::::::::::::::

-1.88

POSITIVE LOGITS

2.59

 apenas

2.31

!!!!!!

2.19

2.16

 HAVE

2.14

 addition

2.11

 sheer

2.11

—

2.08

We

2.05

2.03

Activations Density 0.004%