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

    Neuronpedia

    INDEX
    Explanations

    dates, especially the month of October

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fman
    -0.74
    edIn
    -0.70
    jri
    -0.70
    aird
    -0.66
     attendant
    -0.64
    ettes
    -0.63
    hement
    -0.63
     welf
    -0.63
    eer
    -0.63
    king
    -0.61
    POSITIVE LOGITS
     Surprise
    1.13
     31
    1.02
     29
    0.93
    avia
    0.92
     27
    0.91
     28
    0.90
     2014
    0.90
     26
    0.90
     2015
    0.89
     2013
    0.89
    Act Density 0.031%

    No Known Activations