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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extranjera
    -0.63
     chrétien
    -0.54
     étoit
    -0.54
     vuestros
    -0.54
     dignité
    -0.54
     tää
    -0.54
     literario
    -0.52
     asamblea
    -0.51
     avoient
    -0.51
     Meksika
    -0.50
    POSITIVE LOGITS
     MainAxisSize
    0.95
     etc
    0.91
     kasarigan
    0.90
    WaitGroup
    0.90
    SBATCH
    0.90
    yntaxException
    0.87
     <>",
    0.87
     Fig
    0.85
     فريبيس
    0.84
    تقاوى
    0.84
    Act Density 0.781%

    No Known Activations