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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ci
    0.86
    lh
    0.74
    ls
    0.70
    ODO
    0.69
    ashington
    0.69
    lui
    0.69
    ciende
    0.69
    lte
    0.68
    enzie
    0.68
    น้อง
    0.68
    POSITIVE LOGITS
     showdown
    0.71
    们
    0.68
     initiation
    0.68
     basilica
    0.66
     degassing
    0.64
     widow
    0.63
     bioavailability
    0.63
     volatil
    0.63
     выбо
    0.63
     initi
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.