INDEX

Explanations

The neuron flags mentions of personal-identifying data fields (e.g. name, email, address, telephone number).

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

lists of personal information fields commonly found in forms (such as name, address, email, and phone number).

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

references to personally identifiable information and contact details, especially in forms, registrations, and privacy-policy contexts.

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

 named

0.87

 name

0.85

 NAME

0.84

 bernama

0.79

Name

0.79

 nombre

0.79

Named

0.77

 Named

0.77

name

0.77

 Name

0.75

POSITIVE LOGITS

KURZBESCHREIBUNG

0.61

beschreibung

0.54

surname

0.54

 synonym

0.53

 synonymous

0.52

 tagline

0.52

देह

0.50

 description

0.50

 descriptions

0.50

രിക്കുന്ന

0.50

Activations Density 0.070%

The neuron flags mentions of personal-identifying data fields (e.g. name, email, address, telephone number).

lists of personal information fields commonly found in forms (such as name, address, email, and phone number).

references to personally identifiable information and contact details, especially in forms, registrations, and privacy-policy contexts.

No Comments

No Known Activations

The neuron flags mentions of personal-identifying data fields (e.g. name, email, address, telephone number).

lists of personal information fields commonly found in forms (such as name, address, email, and phone number).

references to personally identifiable information and contact details, especially in forms, registrations, and privacy-policy contexts.

No Comments

No Known Activations