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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bum
    2.18
     BOP
    2.05
     payback
    2.02
     procédés
    2.02
     commentaries
    1.99
     Method
    1.96
     Technique
    1.95
     Methode
    1.90
    techniques
    1.89
    益
    1.89
    POSITIVE LOGITS
     input
    0.73
     raw
    0.69
    input
    0.65
     valores
    0.65
     values
    0.62
    required
    0.55
    values
    0.54
    parameters
    0.52
     string
    0.51
    property
    0.50
    Act Density 3.366%

    No Known Activations