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

    Neuronpedia

    INDEX
    Explanations

    the word "once" and its variations in various contexts

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

    past events or states before a change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataAnnotations
    -0.59
     jPanel
    -0.54
    tyard
    -0.48
    glDelete
    -0.46
    inflater
    -0.44
     dataGridView
    -0.43
    ArgumentParser
    -0.43
     Aptitude
    -0.42
     cartel
    -0.42
    jspx
    -0.41
    POSITIVE LOGITS
     once
    1.78
    once
    1.72
     ONCE
    1.56
    Once
    1.56
     Once
    1.55
    ONCE
    1.45
     egyszer
    0.89
     einmal
    0.87
    一度
    0.83
     einst
    0.81
    Act Density 0.016%

    No Known Activations