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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     современн
    -0.07
    foods
    -0.07
    alten
    -0.07
     AMA
    -0.07
     Hammer
    -0.07
    az
    -0.06
    addy
    -0.06
     כולו
    -0.06
     Lan
    -0.06
    замен
    -0.06
    POSITIVE LOGITS
    .subplot
    0.08
    熵
    0.07
    雇主
    0.07
    strained
    0.07
    뗐
    0.07
     Instances
    0.07
     disparities
    0.07
    组合
    0.07
     indicator
    0.06
     chiropr
    0.06
    Act Density 0.004%

    No Known Activations