INDEX

Explanations

organizations and institutions

The neuron activates on tokens that are part of formal names or specialized technical terms—especially organizational, institutional, or domain‐specific nouns.

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

 ベー

-1.41

 exemplu

-1.36

 ministres

-1.34

 quartiers

-1.33

 contenir

-1.30

 détruire

-1.29

 représentants

-1.28

 planètes

-1.26

鉨

-1.25

 armées

-1.24

POSITIVE LOGITS

to

2.17

get

1.73

 with

1.32

 make

1.29

do

1.29

but

1.28

The

1.25

 kanskje

1.25

 nesten

1.24

1.23

Activations Density 0.387%