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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    suc
    1.23
     Cann
    1.20
    anek
    1.20
     Kott
    1.18
     Colombian
    1.17
     isotropic
    1.17
    ocal
    1.17
     crackers
    1.17
    Carl
    1.16
     Crunch
    1.16
    POSITIVE LOGITS
     fí
    0.66
     내용은
    0.64
    žad
    0.61
    MSO
    0.57
    겠지만
    0.57
    жите
    0.56
     troppo
    0.56
    ロット
    0.56
     mellan
    0.55
    DOM
    0.55
    Act Density 0.310%

    No Known Activations