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

    Neuronpedia

    INDEX
    Explanations

    elements related to research findings, including factors, conclusions, and reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.82
     AssemblyProduct
    -0.77
     насељу
    -0.74
     Wikimedijinoj
    -0.73
    oa̍t
    -0.70
     Paglinawan
    -0.70
     ProtoMessage
    -0.69
     незавершена
    -0.68
    Portail
    -0.67
    脚注の使い方
    -0.66
    POSITIVE LOGITS
    ①
    1.06
     firstly
    1.06
     Firstly
    0.98
    一是
    0.92
     first
    0.90
     ①
    0.89
     pertama
    0.86
    Firstly
    0.83
    ⑴
    0.82
     Pertama
    0.78
    Act Density 0.520%

    No Known Activations