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

    Neuronpedia

    INDEX
    Explanations

    phrases related to persuading or convincing someone to take a specific action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Messieurs
    -1.00
     poichè
    -0.91
     exé
    -0.91
     quoique
    -0.87
     rafra
    -0.85
     Sén
    -0.85
     goû
    -0.82
     véhic
    -0.82
     nuage
    -0.80
     Áng
    -0.80
    POSITIVE LOGITS
    <bos>
    1.02
     click
    0.60
     product
    0.59
     تضيفلها
    0.57
     products
    0.57
     clicking
    0.56
    AsUp
    0.56
     stik
    0.55
     geforce
    0.55
     user
    0.55
    Act Density 0.460%

    No Known Activations