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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation marks in dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.70
     handleMessage
    -0.69
    rouvez
    -0.68
    adeloupe
    -0.61
    avorite
    -0.60
    TargetException
    -0.57
    endgroup
    -0.57
    horabuena
    -0.56
    cellaneous
    -0.56
     disponibilités
    -0.56
    POSITIVE LOGITS
    Yes
    0.79
    yes
    0.70
    Yeah
    0.70
     Yes
    0.67
    We
    0.67
    Oh
    0.66
    It
    0.64
    I
    0.61
    That
    0.61
    But
    0.60
    Act Density 0.069%

    No Known Activations