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

    Neuronpedia

    INDEX
    Explanations

    governmental actions or decisions, such as approvals, settlements, amendments, and bills

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Boss
    -0.71
    antis
    -0.69
    uded
    -0.68
    PLIED
    -0.68
    pure
    -0.66
    Jesus
    -0.65
    God
    -0.64
    mis
    -0.64
    itars
    -0.64
     ancest
    -0.64
    POSITIVE LOGITS
     guidelines
    0.90
     stricter
    0.86
     incentives
    0.84
     provisional
    0.80
     Regulations
    0.79
     regulations
    0.77
     declass
    0.76
     decriminal
    0.75
     reforms
    0.75
     moratorium
    0.75
    Act Density 0.453%

    No Known Activations