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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     douche
    -0.08
     salario
    -0.08
    Routine
    -0.07
    垣
    -0.07
    .elem
    -0.07
    éta
    -0.07
     coursework
    -0.07
     technically
    -0.07
    	glUniform
    -0.07
    \Schema
    -0.07
    POSITIVE LOGITS
    捕
    0.08
    晶
    0.07
     FACT
    0.07
    前提
    0.07
     super
    0.07
    fallback
    0.07
    电商平台
    0.07
    ingers
    0.07
     VAN
    0.07
    助推
    0.07
    Act Density 0.025%

    No Known Activations