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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    acciones
    -0.07
    money
    -0.07
    .prev
    -0.06
    봊
    -0.06
    ennent
    -0.06
                       ↵
    -0.06
     Assumes
    -0.06
    Ps
    -0.06
    basename
    -0.06
     bà
    -0.06
    POSITIVE LOGITS
    쳐
    0.08
    فص
    0.07
    -chief
    0.07
     avoids
    0.07
    쩌
    0.07
     жиз
    0.07
     ineffective
    0.07
     choir
    0.07
     skepticism
    0.07
    鸵
    0.07
    Act Density 0.007%

    No Known Activations