INDEX

Explanations

area, building, house, located

The neuron specializes in spotting tokens that occur in geographic‐relationship phrases—like “county seat” or “intersection of two major Interstate highways”—that describe a place’s administrative or transportation context.

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

 help

-1.58

 this

-1.37

 receive

-1.34

 examples

-1.34

if

-1.34

čnosti

-1.25

 quick

-1.24

 example

-1.23

ıştır

-1.22

特朗普

-1.21

POSITIVE LOGITS

 駅前

1.35

 contextes

1.34

 också

1.27

 beso

1.23

 perpé

1.23

把你

1.23

 téléph

1.20

 siè

1.20

 véhic

1.19

 travaillent

1.18

Activations Density 0.234%