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

    Neuronpedia

    INDEX
    Explanations

    references to political actions and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dirt
    -0.15
    ouz
    -0.14
    dirs
    -0.14
    ohan
    -0.14
    .realm
    -0.14
    Å¡tÄĽ
    -0.14
     Yates
    -0.14
     zbo
    -0.14
     Centers
    -0.14
    лен
    -0.13
    POSITIVE LOGITS
     hust
    0.29
     Conservative
    0.28
     local
    0.27
     locally
    0.26
     residents
    0.26
     Conservatives
    0.26
     MP
    0.26
     Lib
    0.26
     Hust
    0.25
     Liberal
    0.24
    Act Density 0.013%

    No Known Activations