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

    Neuronpedia

    INDEX
    Explanations

    references to swords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sword and foreign translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lacy
    -0.52
     Naughty
    -0.48
    racy
    -0.48
     pops
    -0.48
     Los
    -0.48
     Lax
    -0.47
     Residency
    -0.47
     Mix
    -0.46
     Ne
    -0.45
     local
    -0.45
    POSITIVE LOGITS
    Sword
    1.19
     Sword
    1.15
     sword
    1.11
    sword
    1.04
     swords
    0.98
     Swords
    0.94
     Schwert
    0.84
     espada
    0.81
    剑
    0.65
    AsUp
    0.65
    Act Density 0.004%

    No Known Activations