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

    Neuronpedia

    INDEX
    Explanations

    words related to articles or written pieces

    oai_token-act-pair · gpt-3.5-turbo

    mentions of articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.90
    cffffcc
    -0.77
     Nadu
    -0.75
    ²¾
    -0.74
    elsius
    -0.74
    pter
    -0.73
    edient
    -0.71
    heed
    -0.71
    bered
    -0.70
    inav
    -0.69
    POSITIVE LOGITS
    meal
    1.16
     articles
    0.88
     published
    0.82
     titled
    0.80
     article
    0.77
     detailing
    0.75
     Articles
    0.75
    abal
    0.74
     editor
    0.73
     describing
    0.72
    Act Density 0.025%

    No Known Activations