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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     calon
    1.20
     akt
    0.99
     chairs
    0.97
     recht
    0.96
     v
    0.96
     rob
    0.95
     Meks
    0.94
     fui
    0.93
     kont
    0.93
     lom
    0.92
    POSITIVE LOGITS
    ieran
    0.87
    ници
    0.80
    oinen
    0.79
    sc
    0.79
     meaningless
    0.76
    CodeDict
    0.73
    issage
    0.73
    cially
    0.73
    icing
    0.71
    ص
    0.70
    Act Density 0.000%

    No Known Activations