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

    Neuronpedia

    INDEX
    Explanations

    descriptions portraying something as impressive or appealing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    mediate
    -0.77
    pora
    -0.73
    ugal
    -0.72
     unfit
    -0.68
    avored
    -0.67
     Inquiry
    -0.67
    ãĥĺãĥ©
    -0.65
     condemned
    -0.65
     condemns
    -0.65
    URRENT
    -0.64
    POSITIVE LOGITS
     stuff
    1.00
    ness
    0.94
    nels
    0.94
     GIF
    0.90
     gadgets
    0.90
     dude
    0.89
     guy
    0.88
    ery
    0.86
     kid
    0.85
     sounding
    0.85
    Act Density 0.157%

    No Known Activations