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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "lab."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     virtue
    -0.74
     Perse
    -0.72
     nomine
    -0.70
     Patriot
    -0.65
     Sandy
    -0.65
     Ceres
    -0.63
     withdrawals
    -0.61
    ppel
    -0.61
     Coco
    -0.60
     Aeg
    -0.56
    POSITIVE LOGITS
    stract
    1.23
    urger
    1.18
    yrinth
    1.16
    oard
    1.10
    udget
    1.02
    ylon
    1.02
    bing
    1.01
    raham
    1.00
    riel
    1.00
    erry
    0.98
    Act Density 0.035%

    No Known Activations