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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quotes or statements made by individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nerg
    -0.78
    inary
    -0.71
    lection
    -0.62
     streamed
    -0.62
    owers
    -0.61
     awaken
    -0.61
    swick
    -0.60
    giene
    -0.59
     elect
    -0.57
    cffffcc
    -0.57
    POSITIVE LOGITS
    ometimes
    0.92
    omething
    0.91
    ynthesis
    0.90
    olate
    0.85
    hiba
    0.81
    creen
    0.80
    paces
    0.79
    omorph
    0.76
    ysis
    0.71
    pace
    0.70
    Act Density 0.237%

    No Known Activations