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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     normally
    0.84
     ordinarily
    0.83
    person
    0.83
     sufficiently
    0.83
     manually
    0.82
     rather
    0.81
     diligently
    0.80
     ceas
    0.78
     person
    0.77
     incorrectly
    0.77
    POSITIVE LOGITS
    OF
    0.90
    apagos
    0.88
    犧
    0.88
    볕
    0.87
    hedral
    0.86
     Hồ
    0.86
     Miłos
    0.86
     기대
    0.84
    ofo
    0.84
    ômios
    0.84
    Act Density 0.068%

    No Known Activations