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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal cases and political arguments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.63
    iple
    -0.63
    abouts
    -0.63
    atorium
    -0.62
    rup
    -0.61
    Thirty
    -0.59
    eport
    -0.57
    atars
    -0.56
    kell
    -0.55
    yon
    -0.54
    POSITIVE LOGITS
     namely
    1.37
     respectively
    1.31
     thereby
    1.22
     irrespective
    1.16
     regardless
    1.15
     albeit
    1.14
     whereas
    1.11
     lest
    1.10
     including
    1.09
     culminating
    1.07
    Act Density 1.813%

    No Known Activations