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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    porter
    1.10
     dummy
    1.09
     Terrier
    1.09
    ycling
    1.08
     ug
    1.07
    ब्रेरी
    1.07
     Terence
    1.07
    ollar
    1.07
     Ter
    1.07
    становление
    1.06
    POSITIVE LOGITS
    İ
    1.23
    로운
    1.21
    든
    1.18
    zny
    1.14
     chủ
    1.08
    to
    1.07
     hydroly
    1.06
    catalyzed
    1.03
    dark
    1.03
    1.03
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.