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

    Neuronpedia

    INDEX
    Explanations

    user interface elements and their attributes in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vero
    -0.16
    elon
    -0.16
    irsch
    -0.15
    (\"
    -0.14
    agini
    -0.14
     startY
    -0.14
    fts
    -0.14
     («
    -0.13
    atre
    -0.13
    Ïĥαν
    -0.13
    POSITIVE LOGITS
    ={
    0.30
     {
    0.18
     {...
    0.16
    ={()
    0.16
     =
    0.16
    ={(
    0.16
    Props
    0.16
    ={↵
    0.15
    ="
    0.15
     ={
    0.15
    Act Density 0.004%

    No Known Activations