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

    Neuronpedia

    INDEX
    Explanations

    people's names, especially the name "Philip"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    yrinth
    -0.65
    DERR
    -0.63
    LOAD
    -0.63
    eer
    -0.59
    bnb
    -0.59
    ipeg
    -0.58
    lly
    -0.58
    hips
    -0.57
    inventoryQuantity
    -0.56
     EntityItem
    -0.56
    POSITIVE LOGITS
     Randolph
    0.73
     Morris
    0.71
    son
    0.71
     Seymour
    0.68
    anthrop
    0.64
    entric
    0.63
     Rivers
    0.63
    obar
    0.62
    istine
    0.61
     Pull
    0.61
    Act Density 6.477%

    No Known Activations