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

    Neuronpedia

    INDEX
    Explanations

    names of people and their affiliations in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Republics
    -0.72
     involuntarily
    -0.66
     flamengo
    -0.63
     Portuguesa
    -0.63
     RSSSF
    -0.62
     crdi
    -0.61
     republics
    -0.60
    InsertCommand
    -0.59
    InjectAttribute
    -0.57
     buddha
    -0.56
    POSITIVE LOGITS
    BASEPATH
    0.76
     LUMP
    0.62
    Malaysia
    0.56
     Malaysia
    0.54
    hasMoreElements
    0.53
     Commencez
    0.52
    awtextra
    0.49
     RCMP
    0.49
    reportWebVitals
    0.49
    pacs
    0.48
    Act Density 0.090%

    No Known Activations