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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advocating for or against various political, social, and humanitarian issues

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appeals or calls to action in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.69
     Frie
    -0.68
     Compare
    -0.65
    sheets
    -0.64
     luckily
    -0.63
     fractions
    -0.62
     fortunately
    -0.61
    rote
    -0.61
     anecd
    -0.61
     partName
    -0.60
    POSITIVE LOGITS
    xit
    1.03
    determination
    0.98
    ependence
    0.94
     independence
    0.90
     unification
    0.90
     continuation
    0.89
    inition
    0.89
     restoration
    0.86
     separation
    0.86
    ilee
    0.83
    Act Density 0.850%

    No Known Activations