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

    Neuronpedia

    INDEX
    Explanations

    mentions of military organizations or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     airst
    -0.16
    enko
    -0.15
    Defense
    -0.15
    oji
    -0.15
     Defense
    -0.15
    defense
    -0.14
    ymax
    -0.14
     defense
    -0.14
    -defense
    -0.14
    innie
    -0.14
    POSITIVE LOGITS
     Horse
    0.28
     horse
    0.27
     Huss
    0.26
     Mounted
    0.26
     Caval
    0.25
     cavalry
    0.24
     caval
    0.24
     mounted
    0.23
     mus
    0.23
     cu
    0.23
    Act Density 0.018%

    No Known Activations