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

    Neuronpedia

    INDEX
    Explanations

    instances of key terms or phrases related to grammar and linguistic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YG
    -0.15
    ONO
    -0.14
     Eleven
    -0.14
    ongyang
    -0.14
     Thirty
    -0.14
    /browse
    -0.14
    Thirty
    -0.14
    ngle
    -0.14
    ioni
    -0.13
    ãĤ¤ãĥ¤
    -0.13
    POSITIVE LOGITS
     three
    0.58
     two
    0.57
     four
    0.50
    two
    0.44
    three
    0.44
     five
    0.40
    两个
    0.40
    ä¸ī个
    0.39
     drei
    0.37
     trois
    0.36
    Act Density 0.222%

    No Known Activations