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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly commas and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.71
     säll
    -0.64
     DBNull
    -0.64
     PREG
    -0.62
     linho
    -0.61
     Sma
    -0.59
     iſt
    -0.59
    .[/
    -0.59
    PRNewswire
    -0.58
    XMLSchema
    -0.57
    POSITIVE LOGITS
     etc
    1.16
    etc
    0.95
     그리고
    0.74
     Etc
    0.71
    MigrationBuilder
    0.71
     <=",
    0.70
    =[],
    0.68
     usw
    0.67
    などなど
    0.63
    <bos>
    0.63
    Act Density 0.554%

    No Known Activations