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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    t
    1.34
    the
    1.19
    tar
    1.16
    u
    1.16
    tz
    1.16
    tel
    1.14
    lere
    1.13
    l
    1.11
    0
    1.09
    น
    1.08
    POSITIVE LOGITS
     buono
    1.06
     erections
    1.05
     limitaciones
    1.04
     lesiones
    1.02
     orice
    0.97
     alteraciones
    0.97
     affections
    0.96
     clos
    0.93
     eerst
    0.93
     permainan
    0.93
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.