INDEX

Explanations

countries and cities

The neuron strongly activates on mentions of specific geographic locations (city, state, country 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

on

-1.67

to

-1.37

 from

-1.22

нить

-1.20

тна

-1.16

not

-1.13

aikan

-1.12

 tamén

-1.12

таки

-1.12

 susi

-1.10

POSITIVE LOGITS

何故

1.31

𝑢

1.22

 Однако

1.19

 первая

1.15

 peores

1.14

Westfalen

1.10

 Sebab

1.09

 каждом

1.09

 nhưng

1.07

 писал

1.06

Activations Density 0.135%