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

    Neuronpedia

    INDEX
    Explanations

    references to the Star Wars franchise, particularly its lore and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isay
    -0.17
    ĺ
    -0.17
    istical
    -0.13
    _CPU
    -0.13
     stereotype
    -0.13
    åħ¨åĽ½
    -0.13
    abox
    -0.13
    665
    -0.13
    amo
    -0.12
    ritt
    -0.12
    POSITIVE LOGITS
     canon
    0.48
     canonical
    0.38
     Canon
    0.37
    Canon
    0.36
     cannon
    0.34
    canonical
    0.34
     Canonical
    0.30
    Canonical
    0.29
     continuity
    0.28
     lore
    0.27
    Act Density 0.290%

    No Known Activations