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

    Neuronpedia

    INDEX
    Explanations

    references to the "Star Wars" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erson
    -0.19
    ersion
    -0.17
    erv
    -0.15
    ors
    -0.15
    ÛĮا
    -0.15
    ragon
    -0.14
    yz
    -0.14
    kers
    -0.14
    etics
    -0.14
     Fukushima
    -0.14
    POSITIVE LOGITS
    bucks
    0.23
    vation
    0.21
     Wars
    0.21
    utory
    0.21
     Trek
    0.19
    burst
    0.18
    kest
    0.17
    zman
    0.16
    fish
    0.16
     wars
    0.16
    Act Density 0.012%

    No Known Activations