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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and political matters, including court challenges, legislation, and constitutional principles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hots
    -0.72
    each
    -0.71
    ecause
    -0.69
    utics
    -0.68
    dain
    -0.68
    wic
    -0.68
    borgh
    -0.68
    ornings
    -0.66
    ertodd
    -0.66
    ptives
    -0.66
    POSITIVE LOGITS
    liest
    1.21
    est
    1.17
     portion
    1.12
    iest
    1.08
     realm
    1.07
    osphere
    1.05
     process
    1.05
     equivalent
    1.01
     universe
    1.01
     landscape
    1.00
    Act Density 2.633%

    No Known Activations