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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "start" or its variations suggesting initiation or beginning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.59
     Walkover
    -0.58
    fortawesome
    -0.57
     osobow
    -0.52
    tiérrez
    -0.52
     שוליים
    -0.52
     inoxid
    -0.50
    LEncoder
    -0.47
    <unused23>
    -0.47
     パンチラ
    -0.47
    POSITIVE LOGITS
     started
    1.23
    started
    0.99
     Started
    0.90
    Started
    0.85
     STARTED
    0.82
     begun
    0.79
     began
    0.75
     stopped
    0.68
     empezó
    0.68
     starts
    0.65
    Act Density 0.165%

    No Known Activations