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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events, controversies, and public figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hovah
    -0.73
    )</
    -0.70
     depends
    -0.65
     cannot
    -0.63
     doesnt
    -0.62
    bis
    -0.61
    imum
    -0.60
     ceases
    -0.60
    arta
    -0.59
     determines
    -0.59
    POSITIVE LOGITS
     yesterday
    0.58
     Wednesday
    0.57
    cluded
    0.56
    received
    0.56
     Went
    0.56
     rattled
    0.56
     Thursday
    0.56
     Tuesday
    0.55
     initially
    0.55
     memorable
    0.54
    Act Density 2.106%

    No Known Activations