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

    Neuronpedia

    INDEX
    Explanations

    different types of quotation marks and punctuation related to strings in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opening quotes followed by code-related tokens

    np_acts-logits-general · gemini-2.0-flash

    code syntax delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasIndex
    -0.77
    '));
    -0.72
    ]');
    -0.70
    ioutil
    -0.65
    </h3>
    -0.62
    principalTable
    -0.62
    '){
    -0.62
    /');
    -0.61
    '):
    -0.61
     and
    -0.60
    POSITIVE LOGITS
    ]=="
    1.42
    ("
    1.18
    !("
    1.16
    :@"
    1.11
    //"
    1.08
    __("
    1.06
     _("
    1.04
    ]<<"
    1.04
    ="
    1.01
    _("
    1.01
    Act Density 0.170%

    No Known Activations