INDEX

Explanations

The neuron activates on occurrences of the substring “carbon” (including compounds like hydrocarbons, carbonized, carbon dioxide, carbon black, etc.).

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

carbon monoxide, carbon dioxide, carbon black

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

references to carbon and carbon compounds in scientific or technical 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

樒

-2.92

 bunch

-2.69



-2.67



-2.64

跸

-2.56

genodigd

-2.53

 glimmer

-2.48

 goofy

-2.48

졍

-2.47

POSITIVE LOGITS

 ostensibly

2.78

𖡼

2.75

「

2.73

！】

2.64

 provide

2.59

 seeks

2.53

ization

2.53

ｘ

2.44

has

2.33

⤙

2.27

Activations Density 0.016%

The neuron activates on occurrences of the substring “carbon” (including compounds like hydrocarbons, carbonized, carbon dioxide, carbon black, etc.).

carbon monoxide, carbon dioxide, carbon black

references to carbon and carbon compounds in scientific or technical contexts.

No Known Activations

The neuron activates on occurrences of the substring “carbon” (including compounds like hydrocarbons, carbonized, carbon dioxide, carbon black, etc.).

carbon monoxide, carbon dioxide, carbon black

references to carbon and carbon compounds in scientific or technical contexts.

No Known Activations