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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    公务
    -0.08
    Grammar
    -0.07
    лад
    -0.07
    老头
    -0.07
     dbl
    -0.07
     allegiance
    -0.07
    _exec
    -0.06
    ervisor
    -0.06
    九大精神
    -0.06
     Commun
    -0.06
    POSITIVE LOGITS
    isse
    0.07
    ata
    0.07
    �
    0.06
    ATA
    0.06
    represented
    0.06
    くらい
    0.06
     Charts
    0.06
    ation
    0.06
    :i
    0.06
    ITION
    0.06
    Act Density 0.077%

    No Known Activations