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

    Neuronpedia

    INDEX
    Explanations

    historical references and political terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     chops
    -0.74
     waivers
    -0.71
    arella
    -0.69
    ombs
    -0.68
     signatures
    -0.67
     loopholes
    -0.64
    rollment
    -0.64
     rumors
    -0.64
     glitches
    -0.64
     delet
    -0.63
    POSITIVE LOGITS
    cients
    0.85
     Ancients
    0.85
    ankind
    0.83
     aristocracy
    0.71
     oppressed
    0.67
     mankind
    0.65
     elite
    0.65
     humankind
    0.65
     civilisation
    0.64
     civilization
    0.64
    Act Density 0.683%

    No Known Activations