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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social and economic disparities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.83
    aroo
    -0.81
    within
    -0.79
    terms
    -0.74
    hov
    -0.73
    Ń·
    -0.72
    gram
    -0.72
    çīĪ
    -0.71
    ARY
    -0.71
    roo
    -0.71
    POSITIVE LOGITS
     enthusiasm
    1.05
    luster
    0.95
     specificity
    0.95
     sympathy
    0.94
     manpower
    0.93
     clarity
    0.93
     resources
    0.93
     urgency
    0.93
     opportunities
    0.92
     sophistication
    0.92
    Act Density 0.057%

    No Known Activations