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

    Neuronpedia

    INDEX
    Explanations

    events related to political or historical conspiracies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.87
     Paglinawan
    -0.62
     womit
    -0.56
    astéroïdes
    -0.54
    expandindo
    -0.53
     worauf
    -0.50
    ozof
    -0.49
     <>",
    -0.49
    TokenNameLPAREN
    -0.47
    WebVitals
    -0.46
    POSITIVE LOGITS
     alas
    0.65
     malheureusement
    0.63
     Pamph
    0.62
     réservé
    0.60
     unfortunately
    0.57
     désert
    0.57
     imprimée
    0.57
     sadly
    0.57
     préparé
    0.56
     imprimé
    0.56
    Act Density 0.245%

    No Known Activations