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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ,but
    -0.07
    ()\
    -0.07
    (pro
    -0.07
    teborg
    -0.07
    ters
    -0.06
    	register
    -0.06
    libraries
    -0.06
    },
↵
↵
    -0.06
    ,No
    -0.06
    	make
    -0.06
    POSITIVE LOGITS
     masked
    0.07
     gui
    0.07
     @$_
    0.07
     ROOT
    0.06
     marching
    0.06
    חצי
    0.06
     threatening
    0.06
     trending
    0.06
     affiliate
    0.06
     scl
    0.06
    Act Density 0.002%

    No Known Activations