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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical expressions or notation involving variables and indices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Kal
    -0.79
     Kal
    -0.76
     orde
    -0.75
     kal
    -0.74
     forn
    -0.73
     Beni
    -0.72
     Roz
    -0.72
    alen
    -0.72
    RenderAtEndOf
    -0.71
     kohdetta
    -0.71
    POSITIVE LOGITS
    ^{
    1.53
    )^{
    1.12
    ))^{
    1.09
     ^{
    1.06
    $^{
    1.05
    })^{
    1.01
    }}^{
    1.00
    )|^{
    0.99
     }^{
    0.95
    }^{
    0.95
    Act Density 0.661%

    No Known Activations