INDEX

Explanations

This neuron activates on morphemes that form chemical or biochemical substance names (e.g. roots like “hydro-,” “cor-,” “german-,” “cate-”).

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

hydrocortisone, chitosan, sclerostin

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

chemical compounds and scientific nomenclature in medical or biological texts.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

you

-1.05

 Benutz

-1.02

用心

-1.02

 "\""

-1.01

 Konkurrenz

-0.99

喁

-0.98

}`);

-0.96

!');

-0.96

ﺅ

-0.95

 güns

-0.95

POSITIVE LOGITS

 overall

1.33

 všech

1.23

 tampoco

1.05

iiii

1.04

bø

1.00

rr

1.00

ட்

1.00

 และ

1.00

 acadé

0.98

 average

0.98

Activations Density 0.026%

This neuron activates on morphemes that form chemical or biochemical substance names (e.g. roots like “hydro-,” “cor-,” “german-,” “cate-”).

hydrocortisone, chitosan, sclerostin

chemical compounds and scientific nomenclature in medical or biological texts.

No Comments

No Known Activations

This neuron activates on morphemes that form chemical or biochemical substance names (e.g. roots like “hydro-,” “cor-,” “german-,” “cate-”).

hydrocortisone, chitosan, sclerostin

chemical compounds and scientific nomenclature in medical or biological texts.

No Comments

No Known Activations