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

    Neuronpedia

    INDEX
    Explanations

    dates expressed as a month and year

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods, particularly focusing on dates and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atio
    -0.62
    aline
    -0.62
     grit
    -0.61
    plays
    -0.60
    agy
    -0.59
     enhancement
    -0.57
     feats
    -0.57
     interaction
    -0.56
     conc
    -0.56
     toast
    -0.56
    POSITIVE LOGITS
    DragonMagazine
    0.89
    schild
    0.82
    vez
    0.70
     Kad
    0.69
    llah
    0.68
    cember
    0.67
     Notting
    0.67
     Kass
    0.66
     Borders
    0.66
     Maiden
    0.66
    Act Density 0.261%

    No Known Activations