Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and ancestry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Possessive pronouns followed by family members

    np_acts-logits-general · gemini-2.0-flash

    possessive followed by family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     husbands
    -0.81
     Husband
    -0.76
    Husband
    -0.74
     Spouse
    -0.72
     Families
    -0.67
    husband
    -0.66
     suaminya
    -0.65
     Daughter
    -0.63
     marido
    -0.61
     marito
    -0.61
    POSITIVE LOGITS
     mother
    0.71
     step
    0.60
     الرياضيه
    0.59
     grandmother
    0.59
     older
    0.59
     Aunt
    0.59
     mom
    0.59
     mum
    0.58
     folks
    0.57
     HttpNotFound
    0.56
    Act Density 0.173%

    No Known Activations