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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the commencement of events or periods

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

    start of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varandra
    -0.40
    SourceChecksum
    -0.36
     complémentaires
    -0.35
    úrese
    -0.34
    MessageOf
    -0.34
    adaptiveStyles
    -0.34
    farben
    -0.33
    cessite
    -0.33
    oneofs
    -0.33
    رائه
    -0.32
    POSITIVE LOGITS
    start
    0.85
    Начало
    0.85
     Beginn
    0.85
    inizio
    0.84
    starts
    0.83
     onStart
    0.79
     start
    0.79
    Start
    0.77
     onset
    0.77
     começo
    0.77
    Act Density 0.017%

    No Known Activations