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

    Neuronpedia

    INDEX
    Explanations

    references to the streaming service Netflix

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Netflix

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manuel
    -0.81
    psy
    -0.77
    bos
    -0.68
    imer
    -0.66
    uate
    -0.64
    sie
    -0.63
    inence
    -0.62
     unde
    -0.62
    pse
    -0.62
    oral
    -0.61
    POSITIVE LOGITS
    Netflix
    1.17
     Netflix
    1.10
    netflix
    0.87
     Streaming
    0.87
    flix
    0.85
     Hulu
    0.81
     streaming
    0.81
    Film
    0.79
    Plex
    0.77
    bnb
    0.75
    Act Density 0.009%

    No Known Activations