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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear weapons and arms control issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.88
     Homeless
    -0.81
    ĸļ
    -0.81
    idav
    -0.80
     "$:/
    -0.80
     Ort
    -0.79
     Gallagher
    -0.77
    idas
    -0.75
    Ļ½
    -0.75
    knit
    -0.73
    POSITIVE LOGITS
     warheads
    1.22
     submarines
    1.19
     plutonium
    1.16
     submarine
    1.14
     nuclear
    1.14
     detonated
    1.13
     deton
    1.12
    iferation
    1.10
     missile
    1.09
    utonium
    1.08
    Act Density 0.144%

    No Known Activations