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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    inator
    -0.86
    ena
    -0.82
    arer
    -0.80
    ateurs
    -0.78
    ippery
    -0.77
    inse
    -0.76
    athi
    -0.76
    eva
    -0.76
    anz
    -0.75
    arcity
    -0.74
    POSITIVE LOGITS
     Mean
    0.72
     Conan
    0.69
    £ı
    0.69
     mean
    0.67
     Catalonia
    0.66
     Dull
    0.66
     Clockwork
    0.65
     Noct
    0.64
     Bless
    0.64
     Translation
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.