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

    Neuronpedia

    INDEX
    Explanations

    LaTeX escape sequences or formatting commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EFF
    -0.79
    antd
    -0.77
    EFF
    -0.76
    slidesToShow
    -0.75
     Lég
    -0.72
     Eyre
    -0.70
    uation
    -0.68
    rawDesc
    -0.67
     Sans
    -0.67
     CORD
    -0.66
    POSITIVE LOGITS
     \\
    1.39
    \}\\
    1.37
    \\\
    1.36
    )\\
    1.36
    \\
    1.34
    :\\
    1.29
    }\\
    1.27
    ?\\
    1.26
    $\\
    1.24
     \\\
    1.23
    Act Density 0.096%

    No Known Activations