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

    Neuronpedia

    INDEX
    Explanations

    timestamps within text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     interception
    -0.50
     tempted
    -0.48
     scrap
    -0.47
     compost
    -0.46
     Mub
    -0.45
     Hein
    -0.44
    aten
    -0.44
     faire
    -0.44
     Syri
    -0.44
     freeze
    -0.43
    POSITIVE LOGITS
    Synopsis
    0.74
    Filename
    0.69
    Magazine
    0.66
    Summary
    0.62
    Loading
    0.60
    Contents
    0.60
    yrics
    0.59
    inav
    0.59
    Members
    0.58
    Updated
    0.58
    Act Density 10.201%

    No Known Activations