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

    Neuronpedia

    INDEX
    Explanations

    references to roles and relationships in professional or academic settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cody
    -0.17
     Peggy
    -0.17
    Brandon
    -0.17
     Connie
    -0.16
     Kathleen
    -0.16
     Cynthia
    -0.16
     Brandon
    -0.15
     Moder
    -0.15
    ifu
    -0.15
     Brittany
    -0.15
    POSITIVE LOGITS
    sian
    0.28
     Simon
    0.27
     Gem
    0.26
     Phil
    0.25
     Trace
    0.25
     Gra
    0.24
    Simon
    0.24
     Gill
    0.23
     Graham
    0.22
     Ged
    0.22
    Act Density 0.331%

    No Known Activations