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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ={({
    -0.17
    forge
    -0.16
    æŀIJ
    -0.16
    385
    -0.15
    verse
    -0.15
    eldon
    -0.15
    udu
    -0.15
    arya
    -0.15
    ferred
    -0.14
    stry
    -0.14
    POSITIVE LOGITS
     famil
    0.45
     familia
    0.29
     family
    0.26
     Famil
    0.26
     famille
    0.24
     families
    0.24
    family
    0.21
    家æĹı
    0.21
     FAMILY
    0.21
     Familie
    0.21
    Act Density 0.003%

    No Known Activations