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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions, particularly derivatives and fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </h2>
    -0.51
    </i>
    -0.49
    рд
    -0.48
    ================
    -0.47
     [
    -0.47
     \\
    -0.44
     стр
    -0.43
    Collections
    -0.43
    ,
    -0.43
     leva
    -0.43
    POSITIVE LOGITS
    ExtendWith
    0.86
    RectangleBorder
    0.85
    Démographie
    0.79
    InSection
    0.77
    IntoConstraints
    0.76
    WebVitals
    0.74
    antMatchers
    0.73
    ftance
    0.72
    featureID
    0.72
    WireFormatLite
    0.72
    Act Density 0.457%

    No Known Activations