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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Workbook
    -0.07
    典型案例
    -0.07
    ATOR
    -0.07
    往来
    -0.07
    Dice
    -0.07
    合う
    -0.07
     liner
    -0.07
    יל
    -0.06
    dto
    -0.06
    דבר
    -0.06
    POSITIVE LOGITS
     stret
    0.07
    _weight
    0.07
     chiefly
    0.07
     feeding
    0.06
    payments
    0.06
     additions
    0.06
     resized
    0.06
     superior
    0.06
     RESERVED
    0.06
     woven
    0.06
    Act Density 0.031%

    No Known Activations