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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with nuclear weapons and military options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.10
    3:0.08
    4:0.10
    5:0.04
    6:0.04
    7:0.27
    8:0.04
    9:0.06
    10:0.12
    11:0.06
    Negative Logits
    ean
    -2.03
    vre
    -1.99
    iasis
    -1.79
    oided
    -1.64
    iculty
    -1.57
    eeper
    -1.56
    uliffe
    -1.56
    aunder
    -1.54
    Reviewer
    -1.54
    ickr
    -1.53
    POSITIVE LOGITS
     nuclear
    1.72
     NATO
    1.67
     warheads
    1.65
     plutonium
    1.64
     fists
    1.61
     Guantanamo
    1.59
     Hiroshima
    1.57
     Guam
    1.56
     Guant
    1.48
    SpaceEngineers
    1.48
    Act Density 0.000%

    No Known Activations