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

    Neuronpedia

    INDEX
    Explanations

    references to producers in film and television credits

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    MpServer
    -0.82
    ibaba
    -0.79
    ties
    -0.77
    ocene
    -0.69
    bia
    -0.69
    mia
    -0.68
    carry
    -0.68
    unin
    -0.67
    Leader
    -0.65
    ndum
    -0.64
    POSITIVE LOGITS
     extraord
    1.00
     Steven
    0.94
     Gareth
    0.93
     Constantin
    0.90
     Zack
    0.85
     Aaron
    0.82
     Todd
    0.82
     Damien
    0.81
     Quentin
    0.80
     Alan
    0.80
    Act Density 0.117%

    No Known Activations