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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ‎
    0.73
     overnight
    0.68
    Rewards
    0.68
     bragging
    0.66
    بار
    0.64
    ੁ
    0.63
    :‏
    0.62
     ​
    0.60
    Ска
    0.59
    ‎
    0.58
    POSITIVE LOGITS
     symplect
    0.96
    kelijk
    0.94
     meiosis
    0.93
    빻
    0.92
     esbo
    0.91
     Loki
    0.91
     fermion
    0.89
     vivimos
    0.89
    চরিত
    0.89
     keuze
    0.89
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.