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

    Neuronpedia

    INDEX
    Explanations

    legal and political terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.72
     Correspond
    -0.67
    ordial
    -0.66
     Tune
    -0.66
     Emin
    -0.64
     Complex
    -0.61
     fry
    -0.60
     Networks
    -0.60
     Orient
    -0.59
     Siber
    -0.59
    POSITIVE LOGITS
     outright
    0.97
     legalization
    0.84
     altogether
    0.83
     proposal
    0.82
     because
    0.80
    nesty
    0.78
     proposed
    0.77
     banning
    0.76
     decriminal
    0.76
     championed
    0.75
    Act Density 0.328%

    No Known Activations