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

    Neuronpedia

    INDEX
    Explanations

    words related to information dissemination, such as series, comic, paper, news, update, post, lecture, translation, review, homepage, investigation

    oai_token-act-pair · gpt-3.5-turbo

    references to different forms of media updates or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.72
    anwhile
    -0.71
    enburg
    -0.60
    hovah
    -0.59
    bably
    -0.59
    hammad
    -0.58
     uphe
    -0.58
    aples
    -0.57
    negie
    -0.57
     poorer
    -0.56
    POSITIVE LOGITS
     featuring
    0.83
     highlighting
    0.83
     showcasing
    0.78
     illustrating
    0.76
     EVER
    0.74
    !!!
    0.73
     titled
    0.72
    !
    0.72
    !!!!
    0.71
    !!
    0.71
    Act Density 0.398%

    No Known Activations