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

    Neuronpedia

    INDEX
    Explanations

    sentences and their various forms and endings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     El
    -0.40
    elas
    -0.39
     (
    -0.39
     essa
    -0.38
     lī
    -0.38
     W
    -0.36
    eran
    -0.36
     "
    -0.36
     
    -0.35
    El
    -0.35
    POSITIVE LOGITS
     للمعارف
    1.07
     Paglinawan
    0.92
     Мексичка
    0.90
    GEBURTSDATUM
    0.87
     defaultstate
    0.87
    abestanden
    0.86
    DockStyle
    0.85
     فريبيس
    0.83
    StoryboardSegue
    0.82
     дописавши
    0.82
    Act Density 0.034%

    No Known Activations