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

    Neuronpedia

    INDEX
    Explanations

    mentions of political positions or titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeus
    -0.78
    tip
    -0.76
    angular
    -0.65
    utm
    -0.65
    weak
    -0.65
    Request
    -0.64
     interpol
    -0.64
    ulence
    -0.61
    buy
    -0.60
    respond
    -0.59
    POSITIVE LOGITS
     workforce
    1.03
     profession
    1.01
     society
    0.99
     professions
    0.94
     professional
    0.93
     ranks
    0.90
     academia
    0.90
     majors
    0.89
     athletics
    0.84
     professionally
    0.84
    Act Density 0.657%

    No Known Activations