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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    slightly
    1.15
     slightly
    1.08
     isang
    1.04
     handsome
    0.98
    two
    0.97
    同じ
    0.91
     bebidas
    0.91
    +
    0.89
     थोड़ी
    0.89
    ともに
    0.89
    POSITIVE LOGITS
     unresolved
    1.29
     fraught
    1.24
     irrepar
    1.23
    VIDENCE
    1.22
     detriment
    1.18
     failings
    1.17
     troubling
    1.16
     unchecked
    1.15
     unacceptable
    1.14
     epistem
    1.13
    Act Density 0.740%

    No Known Activations