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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and symbols related to powers and superscripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forn
    -0.89
     orde
    -0.83
     kohdetta
    -0.80
    ver
    -0.75
     transfieras
    -0.75
    alen
    -0.75
    RenderAtEndOf
    -0.75
    es
    -0.74
    }')
    -0.70
    )}-\
    -0.70
    POSITIVE LOGITS
    ^{
    1.95
     ^{
    1.39
    }^{
    1.35
    )^{
    1.24
    $^{
    1.20
     }^{
    1.18
    )|^{
    1.13
    ))^{
    1.10
    ]^{
    1.09
    ^{\
    1.03
    Act Density 0.448%

    No Known Activations