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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critical evaluation and in-depth analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bernatorial
    -0.83
    bus
    -0.75
    ottesville
    -0.74
    BUS
    -0.73
    kr
    -0.73
    orthy
    -0.73
    BILITIES
    -0.73
    igue
    -0.71
    Catalog
    -0.70
    back
    -0.70
    POSITIVE LOGITS
     these
    0.90
     humankind
    0.86
     mankind
    0.85
     existing
    0.80
     those
    0.77
     our
    0.77
     this
    0.76
     successive
    0.74
     certain
    0.73
     incumb
    0.73
    Act Density 0.137%

    No Known Activations