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

    Neuronpedia

    INDEX
    Explanations

    information related to nuclear weapons and nuclear weapon programs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    idas
    -0.74
    MpServer
    -0.68
    idav
    -0.66
     Levant
    -0.64
    odox
    -0.63
    Zip
    -0.62
    Honest
    -0.62
     Barber
    -0.62
    SEA
    -0.61
    Marginal
    -0.61
    POSITIVE LOGITS
     plutonium
    0.97
     warheads
    0.93
    iferation
    0.85
    utonium
    0.85
     submarines
    0.85
     dismant
    0.84
     deton
    0.83
     stockpile
    0.80
     arsen
    0.79
     bunker
    0.77
    Act Density 9.814%

    No Known Activations