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

    Neuronpedia

    INDEX
    Explanations

    references to a wife or spouse

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Haller
    -0.69
     Skar
    -0.66
    Calla
    -0.62
     Calla
    -0.59
    nav
    -0.59
     Poc
    -0.59
    mery
    -0.58
     Blossom
    -0.58
     Merri
    -0.58
    =[[
    -0.58
    POSITIVE LOGITS
     WIFE
    1.07
     wife
    1.02
    Wife
    0.97
    wife
    0.96
     Wife
    0.94
     wives
    0.88
    0.79
     esposa
    0.75
    wives
    0.75
     moglie
    0.74
    Act Density 0.017%

    No Known Activations