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

    Neuronpedia

    INDEX
    Explanations

    titles of books, movies, albums, or collections

    oai_token-act-pair · gpt-3.5-turbo

    titles and references to books and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actu
    -0.74
     advantage
    -0.73
    prise
    -0.71
    rican
    -0.70
     srfAttach
    -0.69
     disadvantage
    -0.69
    iple
    -0.68
    heastern
    -0.68
    ihara
    -0.68
    yers
    -0.67
    POSITIVE LOGITS
     titled
    0.88
     Songs
    0.88
     Dirty
    0.87
     Artemis
    0.86
     Sleeping
    0.83
     Falling
    0.82
     Notting
    0.82
     Goodbye
    0.81
     Fatal
    0.80
     Surv
    0.79
    Act Density 0.226%

    No Known Activations