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

    Neuronpedia

    INDEX
    Explanations

    phrases where something is determined, judged, or evaluated by an authority figure

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Semin
    -0.87
     scrimmage
    -0.85
    APS
    -0.79
     agric
    -0.79
     heartbeat
    -0.75
     childbirth
    -0.74
    EStreamFrame
    -0.74
     Towns
    -0.74
    natureconservancy
    -0.73
    agher
    -0.72
    POSITIVE LOGITS
    phas
    1.76
    ibly
    0.98
    ibility
    0.91
    marked
    0.90
    yssey
    0.90
    leted
    0.88
    phasis
    0.87
    geist
    0.86
    ihad
    0.86
    zik
    0.85
    Act Density 1.165%

    No Known Activations