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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format of a year and numbers that appear to be related to military events or history

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.46
    ⓧ
    -0.68
    
    -0.67
    <?
    -0.65
     implement
    -0.61
     promote
    -0.61
     put
    -0.61
     prepare
    -0.60
     attend
    -0.60
     expand
    -0.60
    POSITIVE LOGITS
     lele
    1.71
     maksi
    1.63
     seksi
    1.61
     saar
    1.59
     pank
    1.50
     uhr
    1.47
     parati
    1.45
     kafe
    1.45
     maroc
    1.45
     moza
    1.45
    Act Density 0.141%

    No Known Activations