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

    Neuronpedia

    INDEX
    Explanations

    news articles on a specific event or topic

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ù
    -0.79
     vola
    -0.70
     assoluto
    -0.69
     herbes
    -0.67
     boxe
    -0.67
     impegno
    -0.66
     pira
    -0.66
     frans
    -0.66
     meras
    -0.66
     calo
    -0.66
    POSITIVE LOGITS
     unspeak
    0.86
     disagre
    0.86
     shenan
    0.85
     apprehen
    0.83
     ineffec
    0.82
     intersper
    0.82
     reluct
    0.79
     reported
    0.77
     reports
    0.77
     vainly
    0.75
    Act Density 0.215%

    No Known Activations