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

    Neuronpedia

    INDEX
    Explanations

    names of publications and works

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hesda
    -0.72
    isans
    -0.72
     landlords
    -0.72
     wield
    -0.71
    uncture
    -0.70
    quickShipAvailable
    -0.70
    hene
    -0.70
    tarians
    -0.69
     Played
    -0.68
    Engineers
    -0.68
    POSITIVE LOGITS
     new
    0.95
     novel
    0.84
     batch
    0.84
     comprehensive
    0.84
     groundbreaking
    0.81
     scathing
    0.79
     masterpiece
    0.78
     sequel
    0.78
     inaugural
    0.77
     blockbuster
    0.76
    Act Density 4.262%

    No Known Activations