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

    Neuronpedia

    INDEX
    Explanations

    mentions of military ranks or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ColumnHeaders
    -0.31
     dø
    -0.31
     behar
    -0.31
    fromnode
    -0.31
     Begegn
    -0.30
     Guards
    -0.29
    WARN
    -0.29
     invokingState
    -0.29
    void
    -0.28
    isée
    -0.28
    POSITIVE LOGITS
     Marine
    0.76
    Marine
    0.71
     Naval
    0.69
    webElementXpaths
    0.69
     Sailor
    0.68
     Sailors
    0.66
     Navy
    0.65
     MARINE
    0.65
     ashore
    0.64
     sailor
    0.64
    Act Density 0.225%

    No Known Activations