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

    Neuronpedia

    INDEX
    Explanations

    important functional components and their interactions within a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -1.40
    Vidite
    -1.37
    NameInMap
    -1.31
     Administrativna
    -1.20
    GEBURTSDATUM
    -1.19
    Personendaten
    -1.19
     '\\;'
    -1.17
    :✨
    -1.15
     мәкал
    -1.10
     Italijani
    -1.09
    POSITIVE LOGITS
    ,
    0.85
    .
    0.81
     
    0.77
     your
    0.69
     is
    0.69
     you
    0.67
     the
    0.66
     I
    0.65
     to
    0.64
     my
    0.63
    Act Density 8.546%

    No Known Activations