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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "more" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Discografia
    -0.81
     africana
    -0.79
    ️
    -0.76
    ⓘ
    -0.76
    (&:
    -0.76
    bufio
    -0.73
     SNL
    -0.71
    ❥
    -0.71
    __()
    -0.71
    ServletException
    -0.71
    POSITIVE LOGITS
     more
    1.62
     MORE
    1.46
    more
    1.39
    MORE
    1.31
     More
    1.31
    More
    1.30
     Moreno
    1.20
     than
    1.12
    emore
    1.05
     Moreira
    1.02
    Act Density 0.090%

    No Known Activations