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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (inflater
    -0.07
    IZED
    -0.07
     miscon
    -0.07
     compassion
    -0.07
    IDAD
    -0.07
    惝
    -0.07
    wró
    -0.07
    xAC
    -0.07
     born
    -0.07
     Csv
    -0.07
    POSITIVE LOGITS
    قود
    0.08
    0.07
     crown
    0.07
     scrap
    0.07
     Clock
    0.07
     ''}↵
    0.07
    մ
    0.06
     autof
    0.06
    ربع
    0.06
     cohorts
    0.06
    Act Density 0.004%

    No Known Activations