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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cons
    -0.07
    imiter
    -0.06
     Eur
    -0.06
     plur
    -0.06
     pile
    -0.06
     erkek
    -0.06
     steer
    -0.06
    -exclusive
    -0.06
    -switch
    -0.06
     porter
    -0.06
    POSITIVE LOGITS
     đời
    0.07
    Iran
    0.07
    예
    0.06
     действительно
    0.06
    ανά
    0.06
     responding
    0.06
     Biom
    0.06
    ческим
    0.06
     affection
    0.06
     jane
    0.06
    Act Density 0.001%

    No Known Activations