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

    Neuronpedia

    INDEX
    Explanations

    dates in the format Month-Year where something significant happened

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating passage of time or chronological events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.71
     surfaces
    -0.66
    Reviewer
    -0.65
    asive
    -0.62
     sauces
    -0.59
    agy
    -0.59
    please
    -0.58
     weave
    -0.57
     please
    -0.57
     persisted
    -0.57
    POSITIVE LOGITS
     course
    0.94
    ruary
    0.86
    course
    0.84
    cember
    0.84
     2011
    0.83
     2013
    0.82
     2012
    0.82
     2014
    0.80
     2009
    0.78
     2015
    0.77
    Act Density 0.066%

    No Known Activations