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

    Neuronpedia

    INDEX
    Explanations

    news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to updates or changes in story content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mississ
    -0.68
     Governors
    -0.67
    scl
    -0.63
     Hirosh
    -0.62
    gt
    -0.58
    isters
    -0.57
     Scheme
    -0.55
    fitting
    -0.55
     grounding
    -0.55
     powerless
    -0.54
    POSITIVE LOGITS
     reprinted
    1.04
     originally
    1.00
     appeared
    0.94
     appears
    0.91
     airs
    0.84
     aired
    0.83
     reproduced
    0.81
    published
    0.77
     tagged
    0.76
     originated
    0.76
    Act Density 0.072%

    No Known Activations