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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /X
    -0.27
     XY
    -0.25
    =X
    -0.22
    <X
    -0.21
     XYZ
    -0.20
     XC
    -0.20
    ,X
    -0.19
     Xm
    -0.18
     XXX
    -0.18
    XXX
    -0.18
    POSITIVE LOGITS
     x
    0.52
    x
    0.44
    	x
    0.39
    (x
    0.32
    $x
    0.31
    Ñħ
    0.31
    {x
    0.30
     Ñħ
    0.28
    )x
    0.28
    .x
    0.27
    Act Density 0.179%

    No Known Activations