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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ŃĶ
    -0.82
    adelphia
    -0.81
    »Ĵ
    -0.78
    Magikarp
    -0.74
     %%
    -0.72
    abytes
    -0.69
     incorpor
    -0.68
    ÏĦ
    -0.67
    umerable
    -0.66
    Cmd
    -0.66
    POSITIVE LOGITS
    enegger
    0.87
    ensor
    0.71
     Selling
    0.70
    eed
    0.69
    hoe
    0.69
    idency
    0.66
    ector
    0.65
    ension
    0.64
    ribing
    0.64
    eeds
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.