INDEX

Explanations

mentions of location-specific phrases or entities

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InterfaceOrientation

-0.07

 kraje

-0.07

unga

-0.07

 Areas

-0.07

 Walls

-0.06

 centres

-0.06

 jails

-0.06

phinx

-0.06

 Locations

-0.06

env

-0.06

POSITIVE LOGITS

 street

0.14

way

0.11

 road

0.10

 block

0.10

eway

0.09

street

0.09

cul

0.09

 tracks

0.08

 interstate

0.08

reet

0.08

Activations Density 0.020%