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

    Neuronpedia

    INDEX
    Explanations

    phrases with mention of political or military actions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to military or political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.75
    inel
    -0.73
     favorably
    -0.72
    awei
    -0.69
    ĻĤ
    -0.69
    romeda
    -0.65
    emort
    -0.64
    Ĭ
    -0.64
    uph
    -0.63
     âĸł
    -0.63
    POSITIVE LOGITS
     Nasa
    0.82
     Fifa
    0.81
    FACE
    0.73
     Kurd
    0.67
     Greenwich
    0.65
    BBC
    0.65
    liam
    0.63
    raising
    0.62
     IOC
    0.62
    Campaign
    0.61
    Act Density 0.089%

    No Known Activations