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

    Neuronpedia

    INDEX
    Explanations

    names and references related to political figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.89
    istically
    -0.74
    culosis
    -0.72
    istical
    -0.72
    ical
    -0.71
     Nanto
    -0.69
    istics
    -0.68
    Interstitial
    -0.67
    stration
    -0.66
     Uriel
    -0.65
    POSITIVE LOGITS
    urdy
    1.00
    ourt
    0.96
    onduct
    0.94
    urry
    0.88
    apers
    0.87
    ott
    0.86
    aleb
    0.85
    ork
    0.85
    atcher
    0.82
    oll
    0.82
    Act Density 5.388%

    No Known Activations