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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    çªĥ
    -0.29
     say
    -0.29
    è¿Ł
    -0.26
    æ´½
    -0.26
    aight
    -0.26
    京
    -0.26
    kö
    -0.24
     user
    -0.24
    é©Ń
    -0.24
    说
    -0.24
    POSITIVE LOGITS
    Unavailable
    0.24
    acula
    0.24
     scrimmage
    0.24
    eroon
    0.23
     refreshed
    0.23
    毫
    0.23
     Everton
    0.23
     Prel
    0.23
     Protection
    0.23
     Compilation
    0.23
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.