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

    Neuronpedia

    INDEX
    Explanations

    familial relationships and family member titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Henry
    -0.46
     Grace
    -0.45
    Grace
    -0.41
    IndentedString
    -0.41
     Sofía
    -0.40
     Emma
    -0.40
     Jack
    -0.39
    Henry
    -0.39
     Margaret
    -0.38
     prosedur
    -0.38
    POSITIVE LOGITS
     Rhonda
    0.79
     Tammy
    0.77
    Tammy
    0.74
    Lori
    0.69
     Lori
    0.68
     Jodi
    0.67
     Randy
    0.65
    Randy
    0.65
     Shelly
    0.65
     Shawn
    0.64
    Act Density 0.136%

    No Known Activations