INDEX

Explanations

states, countries, and cities

The neuron strongly activates on proper nouns denoting geographic locations (e.g. city, county, state, or region names).

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

for

-1.59

 including

-1.44

 that

-1.39

 this

-1.38

包括

-1.37

 each

-1.26

 inclusief

-1.16

it

-1.15

 beserta

-1.13

以及

-1.06

POSITIVE LOGITS

but

1.75

to

1.64

 into

1.59

 grew

1.27

에서

1.25

 where

1.22

 แต่

1.14

raised

1.09

 nhưng

1.09

 parents

1.06

Activations Density 0.091%