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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     penny
    0.47
    ver
    0.46
    hearing
    0.44
     heresy
    0.44
    versal
    0.43
     cannot
    0.43
    ised
    0.42
    odo
    0.42
    uda
    0.42
    ieb
    0.41
    POSITIVE LOGITS
    Registre
    0.56
     боро
    0.56
    ">-->
    0.52
     Сте
    0.50
     мани
    0.49
     Бар
    0.48
     этапе
    0.48
    棫
    0.48
     то
    0.47
    ండే
    0.47
    Act Density 0.000%

    No Known Activations