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

    Neuronpedia

    INDEX
    Explanations

    ellipsis or continuation markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.86
     ''
    -0.79
    Portale
    -0.78
     Mendes
    -0.73
     \"
    -0.73
     tbe
    -0.72
     ``
    -0.71
    ＇
    -0.71
     $\$
    -0.67
     Merk
    -0.66
    POSITIVE LOGITS
     …
    2.15
    …
    1.98
    ”…
    1.74
    )…
    1.71
    ,…
    1.70
    …”
    1.67
    /…
    1.58
     …”
    1.57
    …)
    1.56
    "…
    1.56
    Act Density 0.217%

    No Known Activations