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

    Neuronpedia

    INDEX
    Explanations

    discussions around academic practices and controversial social topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    icz
    -0.72
     oun
    -0.72
     carbohyd
    -0.65
     contests
    -0.63
    atile
    -0.62
     penal
    -0.61
     electr
    -0.61
    heastern
    -0.60
    rued
    -0.60
     deserts
    -0.60
    POSITIVE LOGITS
     Includes
    1.17
     Lots
    1.08
     Appears
    1.08
     Possibly
    1.07
     Seems
    1.06
     Including
    1.05
     Especially
    1.03
     Also
    1.03
     Probably
    1.03
     Contains
    1.03
    Act Density 0.311%

    No Known Activations