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

    Neuronpedia

    INDEX
    Explanations

    specific symbols used for technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    indicators or symbols that reference menus or options in a user interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iqueness
    -1.01
     destro
    -0.98
    onial
    -0.85
    etheless
    -0.83
    acies
    -0.81
    onite
    -0.79
    teenth
    -0.77
    yssey
    -0.77
    erville
    -0.77
    mares
    -0.75
    POSITIVE LOGITS
    _>
    1.40
     >
    0.94
    .<
    0.84
    =>
    0.83
    -->
    0.83
    NOR
    0.81
     (<
    0.77
     <!--
    0.77
    âĸĴ
    0.77
    ALS
    0.76
    Act Density 0.011%

    No Known Activations