INDEX

Explanations

This neuron responds to mentions of appetite regulation and weight-loss interventions (e.g., hunger, satiety, appetite suppression, and related drug names).

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

appetite, hunger, satiety, intake

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

terms related to hunger, appetite, and food intake regulation in medical or scientific contexts.

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

Negative Logits

to

-1.40

 パソコン

-1.26

之事

-1.20

 яйца

-1.18

 kontakta

-1.07

 ufficiali

-1.05

-1.02

 OPERATOR

-1.01

 statunit

-1.00

 Factbook

-1.00

POSITIVE LOGITS

 überweisen

1.34

 Kontroll

1.31

 énergé

1.29

原型

1.29

ıyorum

1.27

kontroll

1.27

 vivía

1.25

Doesn

1.20

škin

1.20

minyak

1.20

Activations Density 0.034%

This neuron responds to mentions of appetite regulation and weight-loss interventions (e.g., hunger, satiety, appetite suppression, and related drug names).

appetite, hunger, satiety, intake

terms related to hunger, appetite, and food intake regulation in medical or scientific contexts.

No Known Activations

This neuron responds to mentions of appetite regulation and weight-loss interventions (e.g., hunger, satiety, appetite suppression, and related drug names).

appetite, hunger, satiety, intake

terms related to hunger, appetite, and food intake regulation in medical or scientific contexts.

No Known Activations