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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Texans
    -0.07
     Sans
    -0.07
     tro
    -0.07
     statutory
    -0.06
    尪
    -0.06
     For
    -0.06
     Charl
    -0.06
     mammals
    -0.06
    裕
    -0.06
    🍍
    -0.06
    POSITIVE LOGITS
    -employed
    0.08
     alters
    0.07
    _checkpoint
    0.07
    .install
    0.07
     aument
    0.07
    arsimp
    0.07
    밈
    0.07
     również
    0.07
    就连
    0.07
    Deferred
    0.07
    Act Density 0.002%

    No Known Activations