INDEX

Explanations

events at home

This neuron detects mentions of a person’s home or place of residence.

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

)‏

-1.48

-1.45

tains

-1.27

ኧ

-1.27

tryck

-1.26

 Vieira

-1.25

eriam

-1.24

raborty

-1.23

!="")

-1.23

).)

-1.21

POSITIVE LOGITS

 españ

1.18

 czasem

1.13

的

1.13

 will

1.12

 serán

1.12

 tekrar

1.09

noir

1.07

 może

1.05

 mismo

1.05

 home

1.04

Activations Density 0.049%