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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ⓝ
    -0.08
    แพ
    -0.07
     makeup
    -0.07
    徼
    -0.07
     Prescription
    -0.07
     сложно
    -0.07
     tob
    -0.07
    venture
    -0.06
     Respond
    -0.06
    .unbind
    -0.06
    POSITIVE LOGITS
     evaluating
    0.07
    同学
    0.07
    材料
    0.07
    >-->↵
    0.07
    ~~~~
    0.07
    erin
    0.07
    学生的
    0.06
     FORM
    0.06
    getitem
    0.06
    	insert
    0.06
    Act Density 0.002%

    No Known Activations