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

    Neuronpedia

    INDEX
    Explanations

    references to civilian life or civilian-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to civilian-related contexts and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ologies
    -0.93
    href
    -0.91
    ology
    -0.82
    rams
    -0.80
    Torrent
    -0.79
    encing
    -0.79
    LER
    -0.77
    ippi
    -0.76
    heet
    -0.76
    TOP
    -0.74
    POSITIVE LOGITS
     casualties
    1.05
     casualty
    0.94
    ization
    0.87
    izational
    0.83
     affairs
    0.81
     airliner
    0.80
     labou
    0.79
     laborers
    0.78
     civilian
    0.78
     contractors
    0.77
    Act Density 0.015%

    No Known Activations