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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    occ
    -0.07
     Gaga
    -0.07
    🐸
    -0.07
    โม
    -0.07
    鳥
    -0.07
     getArguments
    -0.07
     authorities
    -0.07
    佺
    -0.07
    <stdio
    -0.07
    ope
    -0.06
    POSITIVE LOGITS
     knives
    0.07
     lieutenant
    0.07
    -invalid
    0.07
     awaiting
    0.06
     knife
    0.06
     Lieutenant
    0.06
    Window
    0.06
    _git
    0.06
    Infrastructure
    0.06
    LAND
    0.06
    Act Density 0.002%

    No Known Activations