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

    Neuronpedia

    INDEX
    Explanations

    mentions of the "Star Wars" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erson
    -0.17
    andum
    -0.17
    adesh
    -0.17
    yses
    -0.16
    enne
    -0.16
    gens
    -0.16
    kaz
    -0.15
    iser
    -0.15
    ÑĨÑĮ
    -0.15
    eday
    -0.15
    POSITIVE LOGITS
     Wars
    0.29
    ry
    0.27
     Trek
    0.25
     wars
    0.22
    ship
    0.22
    vation
    0.22
    bucks
    0.21
    Wars
    0.21
    ling
    0.20
    burst
    0.20
    Act Density 0.012%

    No Known Activations