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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ̀
    0.91
    ile
    0.90
     household
    0.89
    ı
    0.88
     framework
    0.88
     policy
    0.83
     centimeter
    0.81
     millimeter
    0.81
     belly
    0.81
     arrange
    0.80
    POSITIVE LOGITS
    Decrement
    1.14
    𝖚
    1.08
     garantiert
    1.07
     Reuse
    1.05
     Schne
    1.02
    ς
    1.01
    тных
    1.00
    ueto
    1.00
    Parad
    1.00
    Mutable
    1.00
    Act Density 0.000%

    No Known Activations