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

    Neuronpedia

    INDEX
    Explanations

    statements of mathematical conditions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Integral
    -0.17
     integral
    -0.17
     Haut
    -0.16
     above
    -0.15
    vet
    -0.14
    est
    -0.14
    eries
    -0.14
     py
    -0.14
     aut
    -0.14
    ikel
    -0.14
    POSITIVE LOGITS
    tempt
    0.17
     tract
    0.17
     consequence
    0.15
     ><?
    0.14
     math
    0.14
     Immediate
    0.14
     плод
    0.14
     conservative
    0.14
     consequences
    0.14
     concept
    0.14
    Act Density 0.108%

    No Known Activations