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

    Neuronpedia

    INDEX
    Explanations

    various types of brackets and their contents, particularly for structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )')
    -0.75
    (')
    -0.72
    ',)
    -0.69
     ')
    -0.68
    ')))
    -0.66
    /')
    -0.66
    "})
    -0.66
    ')}}
    -0.66
    ''')
    -0.66
    {}'.
    -0.64
    POSITIVE LOGITS
     }^{[
    1.90
    .[
    1.90
    [
    1.87
    {[
    1.87
     $[
    1.87
    ("[
    1.82
    $[
    1.81
    :[
    1.79
    >[
    1.79
    ?[
    1.78
    Act Density 0.560%

    No Known Activations