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

    Neuronpedia

    INDEX
    Explanations

    terms related to military activities and budget discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arket
    -0.18
     eldre
    -0.16
    hv
    -0.15
    ATCH
    -0.14
    aktion
    -0.14
    noxious
    -0.14
    ione
    -0.14
    liqu
    -0.13
    urtle
    -0.13
    orman
    -0.13
    POSITIVE LOGITS
     Defense
    0.44
     Defence
    0.40
     defense
    0.39
     Pentagon
    0.39
     defence
    0.39
    Defense
    0.38
    defense
    0.33
    -defense
    0.32
     military
    0.30
     Military
    0.29
    Act Density 0.142%

    No Known Activations