INDEX

Explanations

The neuron is primarily sensitive to comparative or contrastive discourse markers (e.g. “different,” “difference,” “substantially,” “another,” “provides,” etc.).

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

words or phrases that distinguish or contrast different concepts or entities.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

statements that emphasize differences or distinctions between things, highlighting contrast or uniqueness.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 እድ

0.55

ссы

0.54

стрии

0.54

пли

0.52

今後

0.52

meros

0.51

𝚂

0.51

越来越多的

0.50

என

0.50

โทษ

0.49

POSITIVE LOGITS

 differs

3.89

 differ

3.69

 differed

3.59

 diferente

3.34

 berbeda

3.31

differ

3.30

แตกต่าง

3.23

 differently

3.22

 differences

3.17

 difer

3.17

Activations Density 1.110%

The neuron is primarily sensitive to comparative or contrastive discourse markers (e.g. “different,” “difference,” “substantially,” “another,” “provides,” etc.).

words or phrases that distinguish or contrast different concepts or entities.

statements that emphasize differences or distinctions between things, highlighting contrast or uniqueness.

No Comments

No Known Activations

The neuron is primarily sensitive to comparative or contrastive discourse markers (e.g. “different,” “difference,” “substantially,” “another,” “provides,” etc.).

words or phrases that distinguish or contrast different concepts or entities.

statements that emphasize differences or distinctions between things, highlighting contrast or uniqueness.

No Comments

No Known Activations