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

    Neuronpedia

    INDEX
    Explanations

    words related to the conclusion or ending of a series or show

    oai_token-act-pair · gpt-3.5-turbo

    references to television series finales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artisan
    -0.79
    Cola
    -0.77
    hari
    -0.74
    uggage
    -0.74
    uge
    -0.73
    lying
    -0.72
    ums
    -0.72
    absolute
    -0.71
    urg
    -0.71
    elong
    -0.70
    POSITIVE LOGITS
     finale
    0.99
     [|
    0.86
     airs
    0.84
     episode
    0.79
     APR
    0.79
     airing
    0.79
     prematurely
    0.78
     reel
    0.77
     arc
    0.71
     aired
    0.70
    Act Density 0.018%

    No Known Activations