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

    Neuronpedia

    INDEX
    Explanations

    proper names of people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaru
    -0.78
    TOR
    -0.76
    exempt
    -0.74
    asks
    -0.73
    PLA
    -0.72
    regulated
    -0.72
    wrapper
    -0.72
    yrim
    -0.71
    leaders
    -0.71
    sites
    -0.71
    POSITIVE LOGITS
     Moore
    1.04
     Allan
    1.01
     Mun
    1.01
     Griffith
    0.99
     Graham
    0.99
     Cohen
    0.99
     Herbert
    0.99
     Miller
    0.98
     Hayes
    0.97
     Lewis
    0.97
    Act Density 0.768%

    No Known Activations