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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those involved in environmental or health-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uber
    -0.82
    unin
    -0.82
    hire
    -0.77
    ogn
    -0.77
    byter
    -0.76
    aber
    -0.75
    aft
    -0.74
    amen
    -0.74
    awar
    -0.74
    technical
    -0.72
    POSITIVE LOGITS
     Patricia
    1.12
     Lynn
    1.12
     Mae
    1.10
     Debbie
    1.07
     Lois
    1.02
     Marie
    1.02
     Michelle
    1.02
     Brenda
    1.00
     Barbara
    1.00
     Veronica
    1.00
    Act Density 0.031%

    No Known Activations