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

    Neuronpedia

    INDEX
    Explanations

    terms related to military defense systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.22
    1:0.03
    2:0.01
    3:0.06
    4:0.06
    5:0.11
    6:0.05
    7:0.01
    8:0.30
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
     elig
    -1.85
     losers
    -1.83
    rats
    -1.82
     happiest
    -1.80
    anth
    -1.71
     happier
    -1.71
    abet
    -1.70
    acci
    -1.68
     Winners
    -1.66
     unhappy
    -1.64
    POSITIVE LOGITS
     missile
    2.36
     capability
    2.29
     Telescope
    2.27
     Ballistic
    2.14
     Missile
    2.12
     missiles
    2.10
    imeter
    2.08
     airborne
    2.05
    weapon
    2.03
     penetrate
    1.99
    Act Density 0.005%

    No Known Activations