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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Phillip
    1.06
     questionable
    1.05
     playfully
    1.04
     December
    1.03
     z
    1.02
     clenched
    1.01
     section
    1.00
     slightly
    0.99
     October
    0.98
     Chapters
    0.97
    POSITIVE LOGITS
    יא
    1.55
    ر
    1.30
    ۰۰
    1.28
    র
    1.21
    itev
    1.19
    ృద్ధి
    1.18
     политика
    1.16
    ক
    1.14
    ০০
    1.10
    âne
    1.10
    Act Density 2.242%

    No Known Activations