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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jeremy
    -0.68
     kevin
    -0.68
     Jared
    -0.67
    Jared
    -0.67
     himself
    -0.65
     Sean
    -0.64
    Jeremy
    -0.63
    Kenneth
    -0.63
     Jason
    -0.63
     Kevin
    -0.62
    POSITIVE LOGITS
     actress
    0.99
     actresses
    0.94
     herself
    0.91
     lady
    0.84
     Elizabeth
    0.84
     princess
    0.82
     housewife
    0.82
     goddess
    0.81
     matron
    0.80
    Elizabeth
    0.80
    Act Density 0.663%

    No Known Activations