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

    Neuronpedia

    INDEX
    Explanations

    the introductory mention of something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    md
    -0.74
    rs
    -0.73
    sav
    -0.68
    borg
    -0.68
    aths
    -0.67
    locked
    -0.67
    tics
    -0.66
    allow
    -0.66
    mbuds
    -0.65
     Nadu
    -0.65
    POSITIVE LOGITS
     thing
    1.18
     responders
    1.11
     impression
    1.06
     baseman
    1.00
     lady
    0.97
     impressions
    0.95
     glance
    0.94
     instinct
    0.93
     step
    0.90
     lesson
    0.90
    Act Density 0.078%

    No Known Activations