INDEX

Explanations

The neuron fires on relatively rare, domain-specific technical or scientific terms—i.e. specialized jargon rather than common words.

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

medical and biological terms

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

technical terminology across different scientific and mathematical domains.

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

 prácticas

-1.18

 schlechter

-1.06

 hilfre

-1.04

してくれた

-1.03

為に

-1.02

置く

-0.99

グー

-0.98

に入れる

-0.97

 sugerencias

-0.95

 äusser

-0.93

POSITIVE LOGITS

 ...............

1.13

が

1.11

peka

1.05

 .............

1.04

ersburg

1.04

 ..............

1.04

 quinn

1.02

bek

1.01

ppings

0.96

).—

0.96

Activations Density 0.143%

The neuron fires on relatively rare, domain-specific technical or scientific terms—i.e. specialized jargon rather than common words.

medical and biological terms

technical terminology across different scientific and mathematical domains.

No Comments

No Known Activations

The neuron fires on relatively rare, domain-specific technical or scientific terms—i.e. specialized jargon rather than common words.

medical and biological terms

technical terminology across different scientific and mathematical domains.

No Comments

No Known Activations