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

    Neuronpedia

    INDEX
    Explanations

    times expressed in the format "hour:minute pm" in news articles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    UCT
    -0.89
     surviv
    -0.86
    enegger
    -0.85
     emanc
    -0.79
    ande
    -0.76
    anmar
    -0.76
     involuntary
    -0.76
     behavi
    -0.76
     suppressed
    -0.75
     tsun
    -0.75
    POSITIVE LOGITS
    Downloadha
    1.14
    facebook
    0.99
    ItemTracker
    0.95
    asp
    0.93
    xxx
    0.93
    org
    0.88
    route
    0.86
    adobe
    0.85
    assetsadobe
    0.83
    11
    0.82
    Act Density 0.340%

    No Known Activations