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

    Neuronpedia

    INDEX
    Explanations

    phrases related to people's names, specifically focusing on individuals named Karen

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Karen" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.84
    cision
    -0.77
    achers
    -0.73
    urers
    -0.73
    udic
    -0.71
    apore
    -0.70
     derogatory
    -0.69
    ruction
    -0.68
    etheus
    -0.67
    ements
    -0.66
    POSITIVE LOGITS
     Sue
    0.87
    aii
    0.78
     Bee
    0.75
     Bei
    0.74
     Borders
    0.74
     Allen
    0.74
     Stark
    0.71
     Draper
    0.71
     Silk
    0.71
    ite
    0.71
    Act Density 0.019%

    No Known Activations