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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bring
    -0.08
     Hole
    -0.07
    র
    -0.07
    -post
    -0.07
     limbs
    -0.07
    disabled
    -0.07
    ado
    -0.07
     PROPERTY
    -0.07
    ult
    -0.07
    .Product
    -0.07
    POSITIVE LOGITS
    ších
    0.06
    .setPositiveButton
    0.06
    Humans
    0.06
    .stderr
    0.06
    的小
    0.06
    ]↵↵↵
    0.06
    .merge
    0.06
     ؟
    0.06
     あ
    0.06
    	rm
    0.06
    Act Density 0.000%

    No Known Activations