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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "Star Wars."

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Star Wars" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.81
    terday
    -0.73
    ecause
    -0.73
     LIA
    -0.72
    udeau
    -0.70
    utics
    -0.69
    eger
    -0.69
    éĹĺ
    -0.68
    ipop
    -0.68
    essee
    -0.67
    POSITIVE LOGITS
     Trek
    1.25
    vation
    1.24
     Wars
    1.24
    Wars
    1.10
    burst
    1.08
    light
    1.08
    bucks
    1.07
    fish
    1.05
    buck
    1.04
    ving
    1.03
    Act Density 0.031%

    No Known Activations