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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the beginning or starting point of an explanation or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebServlet
    -0.78
    ensity
    -0.76
    llary
    -0.76
     EClass
    -0.74
    maline
    -0.71
    )++;
    -0.71
     decathlon
    -0.71
     DBNull
    -0.70
    RTLD
    -0.70
    SharedDtor
    -0.70
    POSITIVE LOGITS
     starting
    0.66
     Start
    0.66
     Starting
    0.63
     starts
    0.63
    Start
    0.62
     start
    0.62
     started
    0.60
    Starting
    0.58
     START
    0.57
     initial
    0.57
    Act Density 0.177%

    No Known Activations