INDEX

Explanations

This neuron fires on words at the start of passages or sentences—especially capitalized opening tokens (e.g. “The,” “Song,” etc.).

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

the definite article "the" in descriptive or narrative contexts.

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

definite articles and possessive markers that introduce or modify noun phrases, especially the definite article at the start of sentences.

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

 সরকার

0.93

 hospitals

0.84

 政府

0.83

 subsidies

0.81

 정부

0.81

 Government

0.79

 सरकार

0.79

 Govt

0.79

 universities

0.74

 GOVERNMENT

0.73

POSITIVE LOGITS

 unassuming

1.53

 enigmatic

1.41

 idyllic

1.35

 playful

1.33

 opulent

1.27

 serene

1.26

 shimmering

1.25

 picturesque

1.24

 whimsical

1.24

 meticulous

1.23

Activations Density 0.817%

This neuron fires on words at the start of passages or sentences—especially capitalized opening tokens (e.g. “The,” “Song,” etc.).

the definite article "the" in descriptive or narrative contexts.

definite articles and possessive markers that introduce or modify noun phrases, especially the definite article at the start of sentences.

No Comments

No Known Activations

This neuron fires on words at the start of passages or sentences—especially capitalized opening tokens (e.g. “The,” “Song,” etc.).

the definite article "the" in descriptive or narrative contexts.

definite articles and possessive markers that introduce or modify noun phrases, especially the definite article at the start of sentences.

No Comments

No Known Activations