INDEX

Explanations

trusted love

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

This neuron consistently lights up on second-person pronouns and imperative constructions (e.g. “you,” “your,” “need to”), i.e. when the text addresses the reader directly.

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

second-person pronouns ("you") in instructional or persuasive text.

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

second-person, promotional or instructional web copy with an advertorial/SEO-spam tone that gives generic advice and calls to action.

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

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_24_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

0.28

and

0.26

or

0.25

0.24

 please

0.24

...

0.23

 song

0.23

0.22

POSITIVE LOGITS

 Hesap

0.28

 Zusätzlich

0.28

<unused355>

0.28

sächlich

0.28

 Faktoren

0.27

<unused339>

0.27

ྪ

0.26

 Meskipun

0.26

 Özellikle

0.26

 Они

0.26

Activations Density 0.594%

trusted love

This neuron consistently lights up on second-person pronouns and imperative constructions (e.g. “you,” “your,” “need to”), i.e. when the text addresses the reader directly.

second-person pronouns ("you") in instructional or persuasive text.

second-person, promotional or instructional web copy with an advertorial/SEO-spam tone that gives generic advice and calls to action.

No Comments

No Known Activations

trusted love

This neuron consistently lights up on second-person pronouns and imperative constructions (e.g. “you,” “your,” “need to”), i.e. when the text addresses the reader directly.

second-person pronouns ("you") in instructional or persuasive text.

second-person, promotional or instructional web copy with an advertorial/SEO-spam tone that gives generic advice and calls to action.

No Comments

No Known Activations