INDEX

Explanations

The neuron activates on numeric tokens (numbers) in the text.

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

physicians and patients

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

organizations or entities mentioned in conjunction with the word "and" in a list or partnership context.

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

 потому

-1.29

 omdat

-1.13

 poiché

-1.13

 because

-1.11

 when

-1.09

opie

-1.06

was

-1.04

if

-1.02

 perché

-1.00

 last

-0.99

POSITIVE LOGITS

 zijne

1.19

ようです

1.13

liferation

1.10

clonal

1.09

 regeringen

1.05

Danh

1.03

嗒

1.03

 hunne

1.02

 veden

1.01

 Pilihan

1.01

Activations Density 0.044%

The neuron activates on numeric tokens (numbers) in the text.

physicians and patients

organizations or entities mentioned in conjunction with the word "and" in a list or partnership context.

No Comments

No Known Activations

The neuron activates on numeric tokens (numbers) in the text.

physicians and patients

organizations or entities mentioned in conjunction with the word "and" in a list or partnership context.

No Comments

No Known Activations