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

    Neuronpedia

    INDEX
    Explanations

    statements related to legal reasoning and qualifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.56
    ctory
    -0.51
     Вікіпе
    -0.50
     Cull
    -0.48
     leetcode
    -0.47
    IGraphics
    -0.46
    gep
    -0.45
    Cull
    -0.45
    line
    -0.44
     refusé
    -0.44
    POSITIVE LOGITS
    __':
    0.84
    "));
    0.79
    "];
    0.79
    #+#
    0.78
    __':
    0.78
    "}>
    0.77
    aarrggbb
    0.77
    "]
    0.75
    '));
    0.75
    LookAnd
    0.73
    Act Density 0.011%

    No Known Activations