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

    Neuronpedia

    INDEX
    Explanations

    numeric values that indicate measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.60
     صوتيه
    -0.58
     jugu
    -0.50
    httphttps
    -0.50
     Acero
    -0.50
     desmotivaciones
    -0.49
    Биография
    -0.49
     ecuador
    -0.48
     rév
    -0.48
     Fleury
    -0.48
    POSITIVE LOGITS
    |.
    0.70
    ("%.
    0.67
    +.
    0.62
     /\.
    0.61
    <bos>
    0.60
    $.
    0.60
     +.
    0.60
    +'.
    0.60
    +".
    0.60
     $.
    0.59
    Act Density 0.638%

    No Known Activations