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

    Neuronpedia

    INDEX
    Explanations

    book recommendations based on gender stereotypes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to education and gender disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Footnote
    -0.71
    Tier
    -0.68
    76561
    -0.68
    ADRA
    -0.66
    everal
    -0.66
    Register
    -0.65
    Save
    -0.65
    Site
    -0.65
    especially
    -0.65
    idan
    -0.64
    POSITIVE LOGITS
     non
    0.74
     theirs
    0.73
     nons
    0.73
     wine
    0.72
     automobiles
    0.70
     ours
    0.70
     rapes
    0.70
     hers
    0.69
     swords
    0.69
     guns
    0.68
    Act Density 0.395%

    No Known Activations