INDEX

Explanations

citations and medical terms

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

bibliographic citations in academic papers, particularly those with reference identifiers like [@bib] or brackets followed by author names.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron responds to numeric tokens—especially citation numbers, bracketed reference indices, and numerical data values.

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

inline academic citations and bibliographic reference markers (bracketed reference notations, citation tags, and cross-reference links).

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

citations or references in academic and scientific text.

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/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

-1.96

);

-1.94

)}_{

-1.91

-1.88

-1.84

dreamstime

-1.80

–

-1.78

 Which

-1.73

fraz

-1.73

 However

-1.71

POSITIVE LOGITS

al

2.13

 zobac

2.05

鈰

1.94

 musisz

1.84

 fiore

1.80

Bety

1.80

镔

1.79

their

1.77

 joten