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

    Neuronpedia

    INDEX
    Explanations

    references to complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    providedIn
    -0.46
    出一
    -0.41
    才行
    -0.39
    quellen
    -0.38
    躇
    -0.38
     Wylie
    -0.37
    ixante
    -0.37
     duties
    -0.36
    istoitu
    -0.36
    esterno
    -0.35
    POSITIVE LOGITS
    一个
    1.71
    一個
    1.59
    个
    1.54
    個
    1.46
     个
    1.31
    了一個
    1.27
     一个
    1.27
    三個
    1.22
    兩個
    1.22
    这个
    1.22
    Act Density 0.094%

    No Known Activations