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

    Neuronpedia

    INDEX
    Explanations

    references to articles or pieces of writing

    oai_token-act-pair · gpt-3.5-turbo

    references to articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.90
    elsius
    -0.77
    cffffcc
    -0.76
    creen
    -0.73
    heed
    -0.70
    pter
    -0.70
    edient
    -0.69
    ascus
    -0.68
     Sector
    -0.67
    inav
    -0.67
    POSITIVE LOGITS
    meal
    0.96
     articles
    0.88
     article
    0.84
     published
    0.80
     titled
    0.74
     essays
    0.74
     describing
    0.73
     detailing
    0.72
     essay
    0.72
    ="#
    0.71
    Act Density 0.024%

    No Known Activations