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

    Neuronpedia

    INDEX
    Explanations

    references to physical objects or locations with a specific message displayed for public viewing

    oai_token-act-pair · gpt-3.5-turbo

    references to signs and placards in a protest or demonstration context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rin
    -0.84
    elsen
    -0.82
    erate
    -0.79
    iciary
    -0.79
     Thro
    -0.75
     Salary
    -0.71
    alin
    -0.68
    ste
    -0.67
    ube
    -0.65
     dyn
    -0.65
    POSITIVE LOGITS
     billboards
    1.07
     erected
    1.04
     banners
    1.03
     proclaiming
    1.03
     advertising
    1.01
     posters
    0.98
     stickers
    0.95
     depicting
    0.93
     slogans
    0.91
     adorned
    0.91
    Act Density 0.102%

    No Known Activations