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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notation, particularly involving derivatives and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Према
    -0.67
    achella
    -0.65
     whoſe
    -0.65
     Ond
    -0.65
     ſmall
    -0.64
     Verſ
    -0.64
     Theſe
    -0.63
     themſelves
    -0.63
     leaſt
    -0.62
     tromper
    -0.62
    POSITIVE LOGITS
    ^{-
    1.10
    )^{-
    1.08
    }^{-
    1.03
     }^{-
    0.92
    ]^{-
    0.81
    ^{-\
    0.76
     ^{-
    0.66
    辞典
    0.63
    ^-
    0.62
     שוליים
    0.62
    Act Density 0.324%
    right)  ^{-1},i\in
    prime}WM)^{-1}=(E[m
    right)  ^{-1}.\end{aligned
    delta_N)^{-1} \left\
    ↵}WM)^{-1}M^{\prime
     $$\Phi^{-1}\bigl\{E
    prime}\Pi^{-1}a(x
     $$\Phi^{-1}\bigl\{E
    pi_{1}^{-1}\lambda_{1
    pi_{1}^{-1}\lambda_{1
     and $\Phi^{-1} $ is the
     that $\n^{-1}(V)$ is
    pi_{1}^{-1}y_{1
    }\Pi↵^{-1}E[a
    {\right)}^{-1}{\mathbf}X
     \bigr\}^{-1}↵\\↵
     where $\Phi^{-1}$ is a given
    ^{\prime}])^{-1}E[a
    {M})^{-1}\hat{M
    text{$g^{-1
    mathcal{P}^{-1}(P)$ such
    }^{-1}$, and a constant
    ):=-f^{-1}(-x)$ (
     than $n^{-1/4}$ convergence
    pr}_2^{-1}(\LL)\leq
    \phi|^{-1}$ \[Eq.
     \ee^{- n^{-r} \tau
    9 bits $a^{-2}$ ($a
    *y**(-1/15))
     μm^−1^
    ↵l**(-1774/
    )/(v**(-1/4))**(
     ((v**(-1/4)/(v