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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and marital statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <=",
    -0.65
     Autorizaciones
    -0.62
    +#+#
    -0.61
    BeginInit
    -0.55
    ژه
    -0.54
    politico
    -0.52
    Amicalement
    -0.52
    dhury
    -0.51
     Autorisations
    -0.51
    (!__
    -0.49
    POSITIVE LOGITS
    الإنجليزية
    0.65
    StructEnd
    0.63
    الحياه
    0.62
     Ethel
    0.62
     Mildred
    0.62
     createState
    0.61
     Gladys
    0.60
     Bertha
    0.60
    LogFactory
    0.58
    Mild
    0.58
    Act Density 0.184%

    No Known Activations