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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and governmental issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ply
    -0.68
     lengths
    -0.63
    ade
    -0.62
    okin
    -0.61
    erald
    -0.60
    cellaneous
    -0.59
    urances
    -0.59
    anship
    -0.59
    complete
    -0.59
    ellen
    -0.58
    POSITIVE LOGITS
     closest
    0.97
    liest
    0.96
    iest
    0.90
     hardest
    0.89
     nearest
    0.88
     weakest
    0.81
     strongest
    0.81
     furthe
    0.77
     dstg
    0.77
     tallest
    0.77
    Act Density 1.944%

    No Known Activations