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

    Neuronpedia

    INDEX
    Explanations

    references to noble families or aristocracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urdu
    -0.17
     $#
    -0.15
    kus
    -0.15
    utch
    -0.14
     bev
    -0.14
    155
    -0.14
    raya
    -0.14
    oras
    -0.14
    aniel
    -0.14
    175
    -0.14
    POSITIVE LOGITS
     Frank
    0.23
     Franken
    0.23
     Carol
    0.23
     Alam
    0.20
    Frank
    0.20
     Counts
    0.19
     Conrad
    0.18
     pÅĻem
    0.18
     Lomb
    0.18
    768
    0.17
    Act Density 0.031%

    No Known Activations