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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orr
    -0.19
    aket
    -0.19
    ee
    -0.15
    itler
    -0.14
    /do
    -0.14
    ees
    -0.14
    ori
    -0.14
    aths
    -0.14
    /body
    -0.14
    umin
    -0.14
    POSITIVE LOGITS
    /pop
    0.21
    ly
    0.20
    ity
    0.18
    ized
    0.18
    ised
    0.15
    lyn
    0.15
    Ùĩ
    0.14
     lẽ
    0.14
    ordion
    0.14
    ITY
    0.14
    Act Density 0.031%

    No Known Activations