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

    Neuronpedia

    INDEX
    Explanations

    positive remarks or compliments within a longer text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     maksi
    -0.90
     kasa
    -0.89
     saar
    -0.82
     alko
    -0.79
     uhr
    -0.76
     jaya
    -0.74
     karton
    -0.73
     Kartu
    -0.72
     makro
    -0.71
     keramik
    -0.71
    POSITIVE LOGITS
     so
    0.75
    <bos>
    0.68
    so
    0.62
    wieś
    0.60
     SO
    0.59
     injust
    0.52
     great
    0.51
     tanta
    0.50
     prestig
    0.50
    SO
    0.50
    Act Density 0.176%

    No Known Activations