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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Restoration
    -0.71
    egu
    -0.70
    oided
    -0.69
     Transmission
    -0.64
     ampl
    -0.63
    ecause
    -0.60
    imens
    -0.60
    lihood
    -0.59
     Yus
    -0.59
    examination
    -0.58
    POSITIVE LOGITS
     naughty
    0.71
     witches
    0.68
    âĶĢâĶĢ
    0.66
    CLASSIFIED
    0.63
    âķIJâķIJ
    0.63
    bryce
    0.62
    ModLoader
    0.62
    dit
    0.61
    20439
    0.61
    iffin
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.