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

    Neuronpedia

    INDEX
    Explanations

    words indicating the start or initiation of an action or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.71
    ThemeOverlay
    -0.63
     שוליים
    -0.62
    べて
    -0.59
    balanceOf
    -0.58
     dikem
    -0.58
    argout
    -0.57
    usercontent
    -0.57
    ('/:
    -0.57
    addGap
    -0.56
    POSITIVE LOGITS
     start
    1.89
     starts
    1.79
     started
    1.78
     Start
    1.74
     begin
    1.74
    start
    1.70
    Start
    1.69
     commence
    1.69
     begun
    1.67
     START
    1.66
    Act Density 0.218%

    No Known Activations