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

    Neuronpedia

    INDEX
    Explanations

    academic formatting and structure in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.15
     autorytatywna
    -1.14
    principalTable
    -0.96
    ItemBackground
    -0.91
    Autoritní
    -0.91
    onViewCreated
    -0.89
    RegressionTest
    -0.89
    :✨
    -0.89
    Rüyada
    -0.89
     Савезне
    -0.88
    POSITIVE LOGITS
    ,
    0.80
    .
    0.77
    ;
    0.64
    [
    0.59
     –
    0.58
    i
    0.57
    /
    0.56
    :
    0.55
    ↵
    0.54
    *
    0.51
    Act Density 0.184%

    No Known Activations