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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving fractions and square roots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nanda
    -0.94
    </i>
    -0.82
    </b>
    -0.76
    Eileen
    -0.73
     Puch
    -0.71
    zepine
    -0.70
    -0.70
    RenderAtEndOf
    -0.70
    herin
    -0.70
     Campion
    -0.69
    POSITIVE LOGITS
    frac
    1.86
    dfrac
    1.39
    mfrac
    1.19
     frac
    1.17
    abstractmethod
    0.80
    fract
    0.76
     fractions
    0.76
    Frac
    0.71
     chapels
    0.71
     sabbia
    0.70
    Act Density 0.147%

    No Known Activations