INDEX

Explanations

cities and districts

This neuron primarily detects mentions of place names or administrative areas (e.g., cities or districts).

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

нием

-1.43

]))

-1.34

恪

-1.30

///</

-1.27

lapsingToolbar

-1.27

暹

-1.24

])));

-1.23

ฺ

-1.23

antado

-1.23

contentLoaded

-1.23

POSITIVE LOGITS

 része

1.31

geführten

1.31

 viaja

1.27

getragen

1.27

leggen

1.22

braz

1.20

 tránsito

1.20

 puentes

1.18

 plástico

1.18

gestellten

1.17

Activations Density 0.057%