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

    Neuronpedia

    INDEX
    Explanations

    references to family members, particularly grandmothers

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "grandmother"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axis
    -0.82
    etheus
    -0.78
    gged
    -0.74
    okers
    -0.74
    uchin
    -0.74
    olog
    -0.71
    urat
    -0.71
    oned
    -0.70
    ologies
    -0.69
    assic
    -0.69
    POSITIVE LOGITS
     grandmother
    0.99
     aunt
    0.96
     grandma
    0.95
    mother
    0.93
    father
    0.91
    stones
    0.84
    parents
    0.81
     Carolyn
    0.77
    arten
    0.75
     Teresa
    0.75
    Act Density 0.007%

    No Known Activations