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

    Neuronpedia

    INDEX
    Explanations

    information related to events, news, and announcements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.56
    ⓧ
    -0.80
    <?
    -0.68
     rehabilitate
    -0.66
    
    -0.66
     stifle
    -0.62
     disperse
    -0.62
     intersper
    -0.61
     triumphed
    -0.60
     endeavored
    -0.60
    POSITIVE LOGITS
     véhic
    1.04
     quoique
    1.00
     Oct
    1.00
     soulign
    0.98
     Nov
    0.97
     Jan
    0.97
     Aug
    0.96
    Oct
    0.94
     considér
    0.94
     Pièces
    0.92
    Act Density 0.156%

    No Known Activations