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

    Neuronpedia

    INDEX
    Explanations

    words related to politics and economics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    "],
    -0.72
     Solution
    -0.68
    aneous
    -0.67
    "]
    -0.66
     guiName
    -0.64
     Bott
    -0.61
    cause
    -0.61
     Spectre
    -0.60
     Passive
    -0.59
     Checking
    -0.59
    POSITIVE LOGITS
     barely
    0.85
     ostensibly
    0.81
     admittedly
    0.80
     arguably
    0.80
     starved
    0.80
     notoriously
    0.79
     desperately
    0.78
    rir
    0.77
     ordinarily
    0.76
     hardly
    0.75
    Act Density 0.271%

    No Known Activations