INDEX

Explanations

residing in or living in

np_acts-logits-general · gemini-2.5-flash-lite

This neuron detects mentions of a person’s place of residence or living location (e.g. “lives in,” “residing in,” “came home to”).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

references to residence and living locations, such as people living in/near places and residential housing contexts.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

the word "lives" (or "lived") when describing where someone resides or has resided.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)$.

-1.30

种类

-1.20

vie

-1.13

釐

-1.12

ofType

-1.12

！！！”

-1.11

ندما

-1.11

となっています

-1.10

\_

-1.10

 которая

-1.09

POSITIVE LOGITS

 également

1.29

 также

1.24

bezpiecz

1.23

 also

1.18

 também

1.17

דה

1.15

женный

1.12

 recibió

1.11

 bezoek

1.09

Также

1.09

Activations Density 0.078%

residing in or living in

This neuron detects mentions of a person’s place of residence or living location (e.g. “lives in,” “residing in,” “came home to”).

references to residence and living locations, such as people living in/near places and residential housing contexts.

the word "lives" (or "lived") when describing where someone resides or has resided.

No Comments

No Known Activations

residing in or living in

This neuron detects mentions of a person’s place of residence or living location (e.g. “lives in,” “residing in,” “came home to”).

references to residence and living locations, such as people living in/near places and residential housing contexts.

the word "lives" (or "lived") when describing where someone resides or has resided.

No Comments

No Known Activations