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

    Neuronpedia

    INDEX
    Explanations

    content related to policy changes and social guidelines regarding education and community standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Montreal
    -0.17
    Canada
    -0.17
     Canadian
    -0.16
    Canadian
    -0.15
     CBC
    -0.15
     ÑĥÑģ
    -0.15
    CBC
    -0.15
    oplay
    -0.15
    achine
    -0.15
     Canada
    -0.15
    POSITIVE LOGITS
     Supports
    0.21
     supports
    0.21
    supports
    0.19
     harm
    0.18
    dings
    0.17
     Sen
    0.17
    OH
    0.15
    heimer
    0.15
     college
    0.15
     College
    0.15
    Act Density 0.017%

    No Known Activations