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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Óscar
    -0.61
    secara
    -0.61
     Compañ
    -0.59
     intéressante
    -0.58
     Darío
    -0.57
    Czym
    -0.56
     Junto
    -0.56
    Fø
    -0.55
    более
    -0.55
    Zapraszamy
    -0.55
    POSITIVE LOGITS
    <bos>
    1.40
     wien
    1.06
     aquare
    0.98
     gmbh
    0.98
     kane
    0.97
     !...
    0.95
     levis
    0.95
     dimentic
    0.94
     jacques
    0.94
     waer
    0.94
    Act Density 0.247%

    No Known Activations