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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     things
    0.68
     laws
    0.60
     permutations
    0.57
     who
    0.56
     when
    0.55
     charities
    0.55
     consequences
    0.55
     mammals
    0.55
     scriptures
    0.53
     companies
    0.52
    POSITIVE LOGITS
     Ayrıca
    0.79
    Provided
    0.68
     allerdings
    0.68
    ufficient
    0.66
     único
    0.66
     επίσης
    0.66
     しかし
    0.65
     상당히
    0.65
    yrıca
    0.63
     ancak
    0.62
    Act Density 0.004%

    No Known Activations