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

    Neuronpedia

    INDEX
    Explanations

    different types of quotation marks and punctuation indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    []);
    -0.73
    ViewFeatures
    -0.68
    Obrázky
    -0.67
    ValueStyle
    -0.65
    )».
    -0.65
    ecap
    -0.62
    %");
    -0.61
    ');?>
    -0.61
    ########.
    -0.61
    '].
    -0.60
    POSITIVE LOGITS
     "
    1.20
     '
    1.10
     “
    1.02
     ‘
    0.94
     „
    0.90
    “
    0.85
     `"
    0.83
     "'
    0.80
     ‚
    0.79
    ]=="
    0.78
    Act Density 0.212%

    No Known Activations