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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Apoll
    0.79
    ↵
    0.74
     Jealous
    0.70
     dallo
    0.69
     apron
    0.68
    への
    0.67
    לות
    0.67
     Associ
    0.66
     Franch
    0.66
     sosok
    0.66
    POSITIVE LOGITS
    arli
    0.83
    凵
    0.80
    끙
    0.74
    ა
    0.74
    cleanup
    0.72
    itimes
    0.72
    ar
    0.72
    challenged
    0.72
     notific
    0.71
    atoms
    0.70
    Act Density 0.003%

    No Known Activations