INDEX

Explanations

geographical locations and regions

This neuron activates on proper geographic place names (countries, regions, cities, bodies of water, etc.).

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

and

-1.70

 with

-1.44

</sup>

-1.34

 bagaimana

-1.30

っこう

-1.25

 стане

-1.25

but

-1.24

рования

-1.20

ையும்

-1.18

ньому

-1.16

POSITIVE LOGITS

饪

1.24

 Outils

1.20

ilustración

1.14

 vanske

1.13

 previously

1.11

 capa

1.11

 puedes

1.10

ઐ

1.09

难以

1.09

就没

1.08

Activations Density 0.121%