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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating procedural or methodological steps

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

    meaning "before" in different languages

    np_acts-logits-general · gemini-2.0-flash

    before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.67
    ſelf
    -0.61
     pleaſure
    -0.60
     OFDb
    -0.58
    bootstrapcdn
    -0.58
    bleib
    -0.58
     Theſe
    -0.57
     Jefus
    -0.56
    Моло
    -0.56
     jealousy
    -0.56
    POSITIVE LOGITS
     sebelumnya
    0.81
     vorher
    0.79
     préalable
    0.78
     beforehand
    0.75
     zuvor
    0.73
     terlebih
    0.73
     previamente
    0.72
     pré
    0.67
     sempat
    0.65
     antes
    0.65
    Act Density 0.256%

    No Known Activations