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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ocking
    -0.64
    ÂŃ
    -0.64
    yden
    -0.64
    edes
    -0.63
     gem
    -0.62
    eria
    -0.60
    utor
    -0.60
    heid
    -0.59
    owing
    -0.59
    oliberal
    -0.57
    POSITIVE LOGITS
    Image
    0.98
    Magikarp
    0.98
     -
    0.78
     ``
    0.74
    ...]
    0.74
     Helpful
    0.71
    Enlarge
    0.71
    ](
    0.70
    =-=-=-=-=-=-=-=-
    0.69
    ................
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.