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

    Neuronpedia

    INDEX
    Explanations

    elements indicative of structured data formats or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     restauration
    -0.35
     remol
    -0.34
    vestream
    -0.34
     western
    -0.32
     directly
    -0.32
     tornillo
    -0.32
     Brunnen
    -0.31
    ByteBuffer
    -0.30
     Literatur
    -0.30
     expansion
    -0.30
    POSITIVE LOGITS
     {
    1.53
     `{
    1.33
    :{
    1.30
    ">{
    1.30
    /{
    1.29
    +{
    1.27
     :{
    1.26
     {
    1.26
    ({
    1.25
     ({
    1.23
    Act Density 0.484%

    No Known Activations