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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    o
    1.38
    en
    1.28
    つまり
    1.21
    ו
    1.10
    足
    1.03
    feas
    0.99
     η
    0.98
    wisdom
    0.97
     sẵn
    0.95
    桑
    0.95
    POSITIVE LOGITS
     affluent
    1.45
    𝙸
    1.34
    盻
    1.30
    口感
    1.28
     appalled
    1.27
    ètent
    1.25
     polypeptides
    1.25
     assailant
    1.24
    cssMode
    1.23
     футболдук
    1.22
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.