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

    Neuronpedia

    INDEX
    Explanations

    phrases related to family relationships and marital status

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

    Appearing before or after a name

    np_acts-logits-general · gemini-2.0-flash

    names following titles like "Ms" or "Mr" or after "married"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Homme
    -0.67
     Grandpa
    -0.65
     Gentlemen
    -0.62
    Grandpa
    -0.59
     grandpa
    -0.58
     gentlemen
    -0.57
     Handsome
    -0.57
     Xander
    -0.56
    Handsome
    -0.56
     Monsieur
    -0.56
    POSITIVE LOGITS
     ModelExpression
    0.73
    saraba
    0.62
    Бахар
    0.60
     danni
    0.59
     Elizabeth
    0.59
    WriteLiteral
    0.57
     ModelRenderer
    0.57
     createState
    0.57
    msgSender
    0.54
     Ann
    0.54
    Act Density 0.224%

    No Known Activations