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

    Neuronpedia

    INDEX
    Explanations

    titles or formats used to describe literary works, movies, or plays

    oai_token-act-pair · gpt-3.5-turbo

    references to novels and films, particularly adaptations and genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okin
    -0.82
    orthy
    -0.82
    cffff
    -0.80
    xus
    -0.77
    aples
    -0.76
    achev
    -0.76
    inks
    -0.73
    usra
    -0.72
    rians
    -0.72
    nyder
    -0.72
    POSITIVE LOGITS
     Artemis
    1.05
     Hannah
    0.88
     Barney
    0.86
     Notting
    0.84
     Samuel
    0.82
     Annie
    0.81
     Rudolph
    0.79
     Martha
    0.78
     Esther
    0.78
     Oscar
    0.77
    Act Density 0.204%

    No Known Activations