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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and expressions related to sets and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vidite
    -0.80
    Castell
    -0.80
    WRENCE
    -0.79
    saurus
    -0.78
     Castell
    -0.77
    llywood
    -0.73
    otoro
    -0.73
    posx
    -0.73
    zsche
    -0.72
     Rar
    -0.72
    POSITIVE LOGITS
     X
    1.34
    X
    1.21
    dX
    1.11
    pX
    1.02
    cX
    0.93
     Xs
    0.91
    XFF
    0.90
    mX
    0.87
    dY
    0.81
    𝑋
    0.79
    Act Density 0.178%

    No Known Activations