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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     axis
    -0.07
     adet
    -0.06
    脱
    -0.06
    (parts
    -0.06
     franchises
    -0.06
    	exit
    -0.06
     Human
    -0.06
    ancybox
    -0.06
     attained
    -0.06
    Apart
    -0.06
    POSITIVE LOGITS
    .Stderr
    0.07
     Kasich
    0.07
    िफ
    0.07
     Shut
    0.06
    record
    0.06
    466
    0.06
     emotional
    0.06
    	Request
    0.06
     münchen
    0.06
     BIND
    0.06
    Act Density 0.003%

    No Known Activations