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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emoc
    -0.16
    nings
    -0.15
    orra
    -0.14
    ilha
    -0.14
     rozh
    -0.14
     Sundays
    -0.14
     Dia
    -0.14
    rá
    -0.14
    Undo
    -0.13
    çº
    -0.13
    POSITIVE LOGITS
     while
    0.34
     poll
    0.27
    while
    0.27
     sleep
    0.27
    	while
    0.25
     whilst
    0.25
    .poll
    0.24
     While
    0.24
     Poll
    0.24
    poll
    0.23
    Act Density 0.106%

    No Known Activations