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

    Neuronpedia

    INDEX
    Explanations

    specific structures or formatting in text, such as brackets or marking denotation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -1.08
    цездатний
    -1.04
    AsUp
    -1.03
     otomatig
    -1.00
     المعيارى
    -0.96
    }\]
    -0.95
    ArrowToggle
    -0.95
    mybatisplus
    -0.94
    rrggbb
    -0.93
    MENAFN
    -0.93
    POSITIVE LOGITS
    tabular
    0.86
    {
    0.80
    ><
    0.74
    enumerate
    0.69
    itemize
    0.65
     {
    0.58
    {{
    0.58
    ${
    0.58
      
    0.57
     
    0.56
    Act Density 0.016%

    No Known Activations