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

    Neuronpedia

    INDEX
    Explanations

    mentions of people in positions of leadership, particularly as presidents or heads of organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     stub
    -1.01
     gaps
    -0.94
    encies
    -0.93
    prep
    -0.92
    nels
    -0.91
     scanner
    -0.91
     complicate
    -0.90
    rouse
    -0.89
    ocr
    -0.88
     relate
    -0.86
    POSITIVE LOGITS
     Towns
    1.11
     Rampage
    1.09
     Friends
    1.08
     Guild
    1.03
     CARD
    0.99
     Nanto
    0.93
     TOUR
    0.93
     Association
    0.92
    interstitial
    0.92
     Tour
    0.91
    Act Density 0.900%

    No Known Activations