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

    Neuronpedia

    INDEX
    Explanations

    function calls related to starting and stopping processes or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting threads or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.43
    <bos>
    -0.39
    zeile
    -0.38
    boxShadow
    -0.37
     dé
    -0.37
     glimpses
    -0.36
     deft
    -0.35
    vey
    -0.35
     glancing
    -0.35
     revisit
    -0.34
    POSITIVE LOGITS
     Start
    0.87
    Start
    0.86
     start
    0.84
    start
    0.82
     igång
    0.77
     startTime
    0.77
     onStart
    0.76
    PreExecute
    0.75
    SBATCH
    0.75
     rozpoczę
    0.74
    Act Density 0.017%

    No Known Activations