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

    Neuronpedia

    INDEX
    Explanations

    occurrences of opening and closing curly braces, typically indicating the start and end of code blocks in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     raiſ
    -0.73
     faſt
    -0.70
     ſever
    -0.66
    ſelves
    -0.66
     deſt
    -0.65
     ſou
    -0.60
     ſta
    -0.60
     ſte
    -0.59
     ſch
    -0.59
    ſelf
    -0.59
    POSITIVE LOGITS
     {
    1.87
     {
    1.21
    ({
    0.92
     \{
    0.91
     ({
    0.87
    {
    0.85
    {
    0.84
     {{
    0.84
    ={
    0.84
     ={
    0.84
    Act Density 0.232%

    No Known Activations