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

    Neuronpedia

    INDEX
    Explanations

    opening and closing curly braces and related structures in data formats or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ので
    -0.78
     SPA
    -0.68
     Steen
    -0.66
     двор
    -0.65
     minus
    -0.62
    }^\
    -0.60
     S
    -0.59
    }_\
    -0.59
    isen
    -0.59
     P
    -0.59
    POSITIVE LOGITS
    ="{
    1.46
    [{
    1.42
    ({
    1.30
    {
    1.30
    ("{
    1.27
    >{
    1.26
    Disliked
    1.25
     {
    1.24
    ("/{
    1.24
    {{{
    1.22
    Act Density 0.694%

    No Known Activations