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

    Neuronpedia

    INDEX
    Explanations

    nested structures and patterns, particularly in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ""))
    -0.70
     ')
    -0.68
     ...
    -0.67
     "")
    -0.64
    isen
    -0.64
    ()")
    -0.62
    $",
    -0.62
    )")
    -0.61
    </s>
    -0.60
    :])
    -0.59
    POSITIVE LOGITS
     {
    1.88
    {
    1.73
    ="{
    1.66
    >{
    1.58
    [{
    1.53
    ({
    1.51
    ={
    1.50
    ("{
    1.50
    "{
    1.49
    /{
    1.46
    Act Density 0.748%

    No Known Activations